The BrainScaleS-2 Accelerated Neuromorphic System With Hybrid Plasticity

Scalable network emulation on analog neuromorphic hardware

We present a novel software feature for the BrainScaleS-2 accelerated neuromorphic platform that facilitates the partitioned emulation of large-scale spiking neural networks. This approach is well suited for deep spiking neural networks and allows for sequential model emulation on undersized neuromorphic resources if the largest recurrent subnetwork and the required neuron fan-in fit on the substrate. We demonstrate the training of two deep spiking neural network models-using the MNIST and EuroSAT datasets-that exceed the physical size constraints of a single-chip BrainScaleS-2 system. The ability to emulate and train networks larger than the substrate provides a pathway for accurate performance evaluation in planned or scaled systems, ultimately advancing the development and understanding of large-scale models and neuromorphic computing architectures.

Memristive Ion Dynamics to Enable Biorealistic Computing

Conventional artificial intelligence (AI) systems are facing bottlenecks due to the fundamental mismatches between AI models, which rely on parallel, in-memory, and dynamic computation, and traditional transistors, which have been designed and optimized for sequential logic operations. This calls for the development of novel computing units beyond transistors. Inspired by the high efficiency and adaptability of biological neural networks, computing systems mimicking the capabilities of biological structures are gaining more attention. Ion-based memristive devices (IMDs), owing to the intrinsic functional similarities to their biological counterparts, hold significant promise for implementing emerging neuromorphic learning and computing algorithms. In this article, we review the fundamental mechanisms of IMDs based on ion drift and diffusion to elucidate the origins of their diverse dynamics. We then examine how these mechanisms operate within different materials to enable IMDs with various types of switching behaviors, leading to a wide range of applications, from emulating biological components to realizing specialized computing requirements. Furthermore, we explore the potential for IMDs to be modified and tuned to achieve customized dynamics, which positions them as one of the most promising hardware candidates for executing bioinspired algorithms with unique specifications. Finally, we identify the challenges currently facing IMDs that hinder their widespread usage and highlight emerging research directions that could significantly benefit from incorporating IMDs.

Parametrizing analog multi-compartment neurons with genetic algorithms

Background

Finding appropriate model parameters for multi-compartmental neuron models can be challenging. Parameters such as the leak and axial conductance are not always directly derivable from neuron observations but are crucial for replicating desired observations. The objective of this study is to replicate the attenuation behavior of an excitatory postsynaptic potential (EPSP) traveling along a linear chain of compartments on the analog BrainScaleS-2 neuromorphic hardware platform.

Methods

In the present publication we use genetic algorithms to find suitable model parameters. They promise parameterization without domain knowledge of the neuromorphic substrate or underlying neuron model. To validate the results of the genetic algorithms, a comprehensive grid search was conducted. Furthermore, trial-to-trial variations in the analog system are counteracted utilizing spike-triggered averaging.

Results and conclusions

The algorithm successfully replicated the desired EPSP attenuation behavior in both single and multi-objective searches illustrating the applicability of genetic algorithms to parameterize analog neuromorphic hardware.

Real-time multicompartment Hodgkin-Huxley neuron emulation on SoC FPGA

Advanced computational models and simulations to unravel the complexities of brain function have known a growing interest in recent years in the field of neurosciences, driven by significant technological progress in computing platforms. Multicompartment models, which capture the detailed morphological and functional properties of neural circuits, represent a significant advancement in this area providing more biological coherence than single compartment modeling. These models serve as a cornerstone for exploring the neural basis of sensory processing, learning paradigms, adaptive behaviors, and neurological disorders. Yet, the high complexity of these models presents a challenge for their real-time implementation, which is essential for exploring alternative therapies for neurological disorders such as electroceutics that rely on biohybrid interaction. Here, we present an accessible, user-friendly, and real-time emulator for multicompartment Hodgkin-Huxley neurons on SoC FPGA. Our system enables real-time emulation of multicompartment neurons while emphasizing cost-efficiency, flexibility, and ease of use. We showcase an implementation utilizing a technology that remains underrepresented in the current literature for this specific application. We anticipate that our system will contribute to the enhancement of computation platforms by presenting an alternative architecture for multicompartment computation. Additionally, it constitutes a step toward developing neuromorphic-based neuroprostheses for bioelectrical therapeutics through an embedded real-time platform running at a similar timescale to biological networks.

Neuromorphic neuromodulation: Towards the next generation of closed-loop neurostimulation

Neuromodulation techniques have emerged as promising approaches for treating a wide range of neurological disorders, precisely delivering electrical stimulation to modulate abnormal neuronal activity. While leveraging the unique capabilities of AI holds immense potential for responsive neurostimulation, it appears as an extremely challenging proposition where real-time (low-latency) processing, low-power consumption, and heat constraints are limiting factors. The use of sophisticated AI-driven models for personalized neurostimulation depends on the back-telemetry of data to external systems (e.g. cloud-based medical mesosystems and ecosystems). While this can be a solution, integrating continuous learning within implantable neuromodulation devices for several applications, such as seizure prediction in epilepsy, is an open question. We believe neuromorphic architectures hold an outstanding potential to open new avenues for sophisticated on-chip analysis of neural signals and AI-driven personalized treatments. With more than three orders of magnitude reduction in the total data required for data processing and feature extraction, the high power- and memory-efficiency of neuromorphic computing to hardware-firmware co-design can be considered as the solution-in-the-making to resource-constraint implantable neuromodulation systems. This perspective introduces the concept of Neuromorphic Neuromodulation, a new breed of closed-loop responsive feedback system. It highlights its potential to revolutionize implantable brain-machine microsystems for patient-specific treatment.

Adaptive spatiotemporal neural networks through complementary hybridization

Processing spatiotemporal data sources with both high spatial dimension and rich temporal information is a ubiquitous need in machine intelligence. Recurrent neural networks in the machine learning domain and bio-inspired spiking neural networks in the neuromorphic computing domain are two promising candidate models for dealing with spatiotemporal data via extrinsic dynamics and intrinsic dynamics, respectively. Nevertheless, these networks have disparate modeling paradigms, which leads to different performance results, making it hard for them to cover diverse data sources and performance requirements in practice. Constructing a unified modeling framework that can effectively and adaptively process variable spatiotemporal data in different situations remains quite challenging. In this work, we propose hybrid spatiotemporal neural networks created by combining the recurrent neural networks and spiking neural networks under a unified surrogate gradient learning framework and a Hessian-aware neuron selection method. By flexibly tuning the ratio between two types of neurons, the hybrid model demonstrates better adaptive ability in balancing different performance metrics, including accuracy, robustness, and efficiency on several typical benchmarks, and generally outperforms conventional single-paradigm recurrent neural networks and spiking neural networks. Furthermore, we evidence the great potential of the proposed network with a robotic task in varying environments. With our proof of concept, the proposed hybrid model provides a generic modeling route to process spatiotemporal data sources in the open world.

A 4096 channel event-based multielectrode array with asynchronous outputs compatible with neuromorphic processors

Bio-signal sensing is pivotal in medical bioelectronics. Traditional methods focus on high sampling rates, leading to large amounts of irrelevant data and high energy consumption. We introduce a self-clocked microelectrode array (MEA) that digitizes bio-signals at the pixel level by encoding changes as asynchronous digital address-events only when they exceed a threshold, significantly reducing off-chip data transmission. This novel MEA comprises a 64 × 64 electrode array, an asynchronous 2D-arbiter, and an Address-Event Representation (AER) communication block. Each pixel operates autonomously, monitoring voltage fluctuations from cellular activity and producing digital pulses for significant changes. Positive and negative signal changes are encoded as "up" and "down" events and are routed off-chip via the asynchronous arbiter. We present results from chip characterization and experimental measurements using electrogenic cells. Additionally, we interface the MEA to a mixed-signal neuromorphic processor, demonstrating a prototype for end-to-end event-based bio-signal sensing and processing.

Brain-inspired biomimetic robot control: a review

Complex robotic systems, such as humanoid robot hands, soft robots, and walking robots, pose a challenging control problem due to their high dimensionality and heavy non-linearities. Conventional model-based feedback controllers demonstrate robustness and stability but struggle to cope with the escalating system design and tuning complexity accompanying larger dimensions. In contrast, data-driven methods such as artificial neural networks excel at representing high-dimensional data but lack robustness, generalization, and real-time adaptiveness. In response to these challenges, researchers are directing their focus to biological paradigms, drawing inspiration from the remarkable control capabilities inherent in the human body. This has motivated the exploration of new control methods aimed at closely emulating the motor functions of the brain given the current insights in neuroscience. Recent investigation into these Brain-Inspired control techniques have yielded promising results, notably in tasks involving trajectory tracking and robot locomotion. This paper presents a comprehensive review of the foremost trends in biomimetic brain-inspired control methods to tackle the intricacies associated with controlling complex robotic systems.

Impact of quantum and neuromorphic computing on biomolecular simulations: Current status and perspectives

New high-performance computing architectures are becoming operative, in addition to exascale computers. Quantum computers (QC) solve optimization problems with unprecedented efficiency and speed, while neuromorphic hardware (NMH) simulates neural network dynamics. Albeit, at the moment, both find no practical use in all atom biomolecular simulations, QC might be exploited in the not-too-far future to simulate systems for which electronic degrees of freedom play a key and intricate role for biological function, whereas NMH might accelerate molecular dynamics simulations with low energy consumption. Machine learning and artificial intelligence algorithms running on NMH and QC could assist in the analysis of data and speed up research. If these implementations are successful, modular supercomputing could further dramatically enhance the overall computing capacity by combining highly optimized software tools into workflows, linking these architectures to exascale computers.

Signatures of hierarchical temporal processing in the mouse visual system

A core challenge for the brain is to process information across various timescales. This could be achieved by a hierarchical organization of temporal processing through intrinsic mechanisms (e.g., recurrent coupling or adaptation), but recent evidence from spike recordings of the rodent visual system seems to conflict with this hypothesis. Here, we used an optimized information-theoretic and classical autocorrelation analysis to show that information- and correlation timescales of spiking activity increase along the anatomical hierarchy of the mouse visual system under visual stimulation, while information-theoretic predictability decreases. Moreover, intrinsic timescales for spontaneous activity displayed a similar hierarchy, whereas the hierarchy of predictability was stimulus-dependent. We could reproduce these observations in a basic recurrent network model with correlated sensory input. Our findings suggest that the rodent visual system employs intrinsic mechanisms to achieve longer integration for higher cortical areas, while simultaneously reducing predictability for an efficient neural code.

Direct training high-performance deep spiking neural networks: a review of theories and methods

Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial neural networks (ANNs), in virtue of their high biological plausibility, rich spatial-temporal dynamics, and event-driven computation. The direct training algorithms based on the surrogate gradient method provide sufficient flexibility to design novel SNN architectures and explore the spatial-temporal dynamics of SNNs. According to previous studies, the performance of models is highly dependent on their sizes. Recently, direct training deep SNNs have achieved great progress on both neuromorphic datasets and large-scale static datasets. Notably, transformer-based SNNs show comparable performance with their ANN counterparts. In this paper, we provide a new perspective to summarize the theories and methods for training deep SNNs with high performance in a systematic and comprehensive way, including theory fundamentals, spiking neuron models, advanced SNN models and residual architectures, software frameworks and neuromorphic hardware, applications, and future trends.

Active Inference for Learning and Development in Embodied Neuromorphic Agents

Taking inspiration from humans can help catalyse embodied AI solutions for important real-world applications. Current human-inspired tools include neuromorphic systems and the developmental approach to learning. However, this developmental neurorobotics approach is currently lacking important frameworks for human-like computation and learning. We propose that human-like computation is inherently embodied, with its interface to the world being neuromorphic, and its learning processes operating across different timescales. These constraints necessitate a unified framework: active inference, underpinned by the free energy principle (FEP). Herein, we describe theoretical and empirical support for leveraging this framework in embodied neuromorphic agents with autonomous mental development. We additionally outline current implementation approaches (including toolboxes) and challenges, and we provide suggestions for next steps to catalyse this important field.

BiœmuS: A new tool for neurological disorders studies through real-time emulation and hybridization using biomimetic Spiking Neural Network

Characterization and modeling of biological neural networks has emerged as a field driving significant advancements in our understanding of brain function and related pathologies. As of today, pharmacological treatments for neurological disorders remain limited, pushing the exploration of promising alternative approaches such as electroceutics. Recent research in bioelectronics and neuromorphic engineering have fostered the development of the new generation of neuroprostheses for brain repair. However, achieving their full potential necessitates a deeper understanding of biohybrid interaction. In this study, we present a novel real-time, biomimetic, cost-effective and user-friendly neural network capable of real-time emulation for biohybrid experiments. Our system facilitates the investigation and replication of biophysically detailed neural network dynamics while prioritizing cost-efficiency, flexibility and ease of use. We showcase the feasibility of conducting biohybrid experiments using standard biophysical interfaces and a variety of biological cells as well as real-time emulation of diverse network configurations. We envision our system as a crucial step towards the development of neuromorphic-based neuroprostheses for bioelectrical therapeutics, enabling seamless communication with biological networks on a comparable timescale. Its embedded real-time functionality enhances practicality and accessibility, amplifying its potential for real-world applications in biohybrid experiments.

Memristor-based adaptive neuromorphic perception in unstructured environments

Efficient operation of control systems in robotics or autonomous driving targeting real-world navigation scenarios requires perception methods that allow them to understand and adapt to unstructured environments with good accuracy, adaptation, and generality, similar to humans. To address this need, we present a memristor-based differential neuromorphic computing, perceptual signal processing, and online adaptation method providing neuromorphic style adaptation to external sensory stimuli. The adaptation ability and generality of this method are confirmed in two application scenarios: object grasping and autonomous driving. In the former, a robot hand realizes safe and stable grasping through fast ( ~ 1 ms) adaptation based on the tactile object features with a single memristor. In the latter, decision-making information of 10 unstructured environments in autonomous driving is extracted with an accuracy of 94% with a 40×25 memristor array. By mimicking human low-level perception mechanisms, the electronic neuromorphic circuit-based method achieves real-time adaptation and high-level reactions to unstructured environments.

Mapless mobile robot navigation at the edge using self-supervised cognitive map learners

Navigation of mobile agents in unknown, unmapped environments is a critical task for achieving general autonomy. Recent advancements in combining Reinforcement Learning with Deep Neural Networks have shown promising results in addressing this challenge. However, the inherent complexity of these approaches, characterized by multi-layer networks and intricate reward objectives, limits their autonomy, increases memory footprint, and complicates adaptation to energy-efficient edge hardware. To overcome these challenges, we propose a brain-inspired method that employs a shallow architecture trained by a local learning rule for self-supervised navigation in uncharted environments. Our approach achieves performance comparable to a state-of-the-art Deep Q Network (DQN) method with respect to goal-reaching accuracy and path length, with a similar (slightly lower) number of parameters, operations, and training iterations. Notably, our self-supervised approach combines novelty-based and random walks to alleviate the need for objective reward definition and enhance agent autonomy. At the same time, the shallow architecture and local learning rule do not call for error backpropagation, decreasing the memory overhead and enabling implementation on edge neuromorphic processors. These results contribute to the potential of embodied neuromorphic agents utilizing minimal resources while effectively handling variability.

Advancing brain-inspired computing with hybrid neural networks

Brain-inspired computing, drawing inspiration from the fundamental structure and information-processing mechanisms of the human brain, has gained significant momentum in recent years. It has emerged as a research paradigm centered on brain-computer dual-driven and multi-network integration. One noteworthy instance of this paradigm is the hybrid neural network (HNN), which integrates computer-science-oriented artificial neural networks (ANNs) with neuroscience-oriented spiking neural networks (SNNs). HNNs exhibit distinct advantages in various intelligent tasks, including perception, cognition and learning. This paper presents a comprehensive review of HNNs with an emphasis on their origin, concepts, biological perspective, construction framework and supporting systems. Furthermore, insights and suggestions for potential research directions are provided aiming to propel the advancement of the HNN paradigm.

Darwin3: a large-scale neuromorphic chip with a novel ISA and on-chip learning

Spiking neural networks (SNNs) are gaining increasing attention for their biological plausibility and potential for improved computational efficiency. To match the high spatial-temporal dynamics in SNNs, neuromorphic chips are highly desired to execute SNNs in hardware-based neuron and synapse circuits directly. This paper presents a large-scale neuromorphic chip named Darwin3 with a novel instruction set architecture, which comprises 10 primary instructions and a few extended instructions. It supports flexible neuron model programming and local learning rule designs. The Darwin3 chip architecture is designed in a mesh of computing nodes with an innovative routing algorithm. We used a compression mechanism to represent synaptic connections, significantly reducing memory usage. The Darwin3 chip supports up to 2.35 million neurons, making it the largest of its kind on the neuron scale. The experimental results showed that the code density was improved by up to 28.3× in Darwin3, and that the neuron core fan-in and fan-out were improved by up to 4096× and 3072× by connection compression compared to the physical memory depth. Our Darwin3 chip also provided memory saving between 6.8× and 200.8× when mapping convolutional spiking neural networks onto the chip, demonstrating state-of-the-art performance in accuracy and latency compared to other neuromorphic chips.

ExaFlexHH: an exascale-ready, flexible multi-FPGA library for biologically plausible brain simulations

Introduction

In-silico simulations are a powerful tool in modern neuroscience for enhancing our understanding of complex brain systems at various physiological levels. To model biologically realistic and detailed systems, an ideal simulation platform must possess: (1) high performance and performance scalability, (2) flexibility, and (3) ease of use for non-technical users. However, most existing platforms and libraries do not meet all three criteria, particularly for complex models such as the Hodgkin-Huxley (HH) model or for complex neuron-connectivity modeling such as gap junctions.

Methods

This work introduces ExaFlexHH, an exascale-ready, flexible library for simulating HH models on multi-FPGA platforms. Utilizing FPGA-based Data-Flow Engines (DFEs) and the dataflow programming paradigm, ExaFlexHH addresses all three requirements. The library is also parameterizable and compliant with NeuroML, a prominent brain-description language in computational neuroscience. We demonstrate the performance scalability of the platform by implementing a highly demanding extended-Hodgkin-Huxley (eHH) model of the Inferior Olive using ExaFlexHH.

Results

Model simulation results show linear scalability for unconnected networks and near-linear scalability for networks with complex synaptic plasticity, with a 1.99 × performance increase using two FPGAs compared to a single FPGA simulation, and 7.96 × when using eight FPGAs in a scalable ring topology. Notably, our results also reveal consistent performance efficiency in GFLOPS per watt, further facilitating exascale-ready computing speeds and pushing the boundaries of future brain-simulation platforms.

Discussion

The ExaFlexHH library shows superior resource efficiency, quantified in FLOPS per hardware resources, benchmarked against other competitive FPGA-based brain simulation implementations.

Closing the loop: High-speed robotics with accelerated neuromorphic hardware

The BrainScaleS-2 system is an established analog neuromorphic platform with versatile applications in the diverse fields of computational neuroscience and spike-based machine learning. In this work, we extend the system with a configurable realtime event interface that enables a tight coupling of its distinct analog network core to external sensors and actuators. The 1,000-fold acceleration of the emulated nerve cells allows us to target high-speed robotic applications that require precise timing on a microsecond scale. As a showcase, we present a closed-loop setup for commuting brushless DC motors: we utilize PyTorch to train a spiking neural network emulated on the analog substrate to control an electric motor from a sensory event stream. The presented system enables research in the area of event-driven controllers for high-speed robotics, including self-supervised and biologically inspired online learning for such applications.

Neuromorphic hardware for somatosensory neuroprostheses

In individuals with sensory-motor impairments, missing limb functions can be restored using neuroprosthetic devices that directly interface with the nervous system. However, restoring the natural tactile experience through electrical neural stimulation requires complex encoding strategies. Indeed, they are presently limited in effectively conveying or restoring tactile sensations by bandwidth constraints. Neuromorphic technology, which mimics the natural behavior of neurons and synapses, holds promise for replicating the encoding of natural touch, potentially informing neurostimulation design. In this perspective, we propose that incorporating neuromorphic technologies into neuroprostheses could be an effective approach for developing more natural human-machine interfaces, potentially leading to advancements in device performance, acceptability, and embeddability. We also highlight ongoing challenges and the required actions to facilitate the future integration of these advanced technologies.

SHIP: a computational framework for simulating and validating novel technologies in hardware spiking neural networks

Investigations in the field of spiking neural networks (SNNs) encompass diverse, yet overlapping, scientific disciplines. Examples range from purely neuroscientific investigations, researches on computational aspects of neuroscience, or applicative-oriented studies aiming to improve SNNs performance or to develop artificial hardware counterparts. However, the simulation of SNNs is a complex task that can not be adequately addressed with a single platform applicable to all scenarios. The optimization of a simulation environment to meet specific metrics often entails compromises in other aspects. This computational challenge has led to an apparent dichotomy of approaches, with model-driven algorithms dedicated to the detailed simulation of biological networks, and data-driven algorithms designed for efficient processing of large input datasets. Nevertheless, material scientists, device physicists, and neuromorphic engineers who develop new technologies for spiking neuromorphic hardware solutions would find benefit in a simulation environment that borrows aspects from both approaches, thus facilitating modeling, analysis, and training of prospective SNN systems. This manuscript explores the numerical challenges deriving from the simulation of spiking neural networks, and introduces SHIP, Spiking (neural network) Hardware In PyTorch, a numerical tool that supports the investigation and/or validation of materials, devices, small circuit blocks within SNN architectures. SHIP facilitates the algorithmic definition of the models for the components of a network, the monitoring of states and output of the modeled systems, and the training of the synaptic weights of the network, by way of user-defined unsupervised learning rules or supervised training techniques derived from conventional machine learning. SHIP offers a valuable tool for researchers and developers in the field of hardware-based spiking neural networks, enabling efficient simulation and validation of novel technologies.

Temporal dendritic heterogeneity incorporated with spiking neural networks for learning multi-timescale dynamics

It is widely believed the brain-inspired spiking neural networks have the capability of processing temporal information owing to their dynamic attributes. However, how to understand what kind of mechanisms contributing to the learning ability and exploit the rich dynamic properties of spiking neural networks to satisfactorily solve complex temporal computing tasks in practice still remains to be explored. In this article, we identify the importance of capturing the multi-timescale components, based on which a multi-compartment spiking neural model with temporal dendritic heterogeneity, is proposed. The model enables multi-timescale dynamics by automatically learning heterogeneous timing factors on different dendritic branches. Two breakthroughs are made through extensive experiments: the working mechanism of the proposed model is revealed via an elaborated temporal spiking XOR problem to analyze the temporal feature integration at different levels; comprehensive performance benefits of the model over ordinary spiking neural networks are achieved on several temporal computing benchmarks for speech recognition, visual recognition, electroencephalogram signal recognition, and robot place recognition, which shows the best-reported accuracy and model compactness, promising robustness and generalization, and high execution efficiency on neuromorphic hardware. This work moves neuromorphic computing a significant step toward real-world applications by appropriately exploiting biological observations.

Elucidating multifinal and equifinal pathways to developmental disorders by constructing real-world neurorobotic models

Vigorous research has been conducted to accumulate biological and theoretical knowledge about neurodevelopmental disorders, including molecular, neural, computational, and behavioral characteristics; however, these findings remain fragmentary and do not elucidate integrated mechanisms. An obstacle is the heterogeneity of developmental pathways causing clinical phenotypes. Additionally, in symptom formations, the primary causes and consequences of developmental learning processes are often indistinguishable. Herein, we review developmental neurorobotic experiments tackling problems related to the dynamic and complex properties of neurodevelopmental disorders. Specifically, we focus on neurorobotic models under predictive processing lens for the study of developmental disorders. By constructing neurorobotic models with predictive processing mechanisms of learning, perception, and action, we can simulate formations of integrated causal relationships among neurodynamical, computational, and behavioral characteristics in the robot agents while considering developmental learning processes. This framework has the potential to bind neurobiological hypotheses (excitation-inhibition imbalance and functional disconnection), computational accounts (unusual encoding of uncertainty), and clinical symptoms. Developmental neurorobotic approaches may serve as a complementary research framework for integrating fragmented knowledge and overcoming the heterogeneity of neurodevelopmental disorders.

Event-driven adaptive optical neural network

We present an adaptive optical neural network based on a large-scale event-driven architecture. In addition to changing the synaptic weights (synaptic plasticity), the optical neural network's structure can also be reconfigured enabling various functionalities (structural plasticity). Key building blocks are wavelength-addressable artificial neurons with embedded phase-change materials that implement nonlinear activation functions and nonvolatile memory. Using multimode focusing, the activation function features both excitatory and inhibitory responses and shows a reversible switching contrast of 3.2 decibels. We train the neural network to distinguish between English and German text samples via an evolutionary algorithm. We investigate both the synaptic and structural plasticity during the training process. On the basis of this concept, we realize a large-scale network consisting of 736 subnetworks with 16 phase-change material neurons each. Overall, 8398 neurons are functional, highlighting the scalability of the photonic architecture.

Gradient-based feature-attribution explainability methods for spiking neural networks

Introduction

Spiking neural networks (SNNs) are a model of computation that mimics the behavior of biological neurons. SNNs process event data (spikes) and operate more sparsely than artificial neural networks (ANNs), resulting in ultra-low latency and small power consumption. This paper aims to adapt and evaluate gradient-based explainability methods for SNNs, which were originally developed for conventional ANNs.

Methods

The adapted methods aim to create input feature attribution maps for SNNs trained through backpropagation that process either event-based spiking data or real-valued data. The methods address the limitations of existing work on explainability methods for SNNs, such as poor scalability, limited to convolutional layers, requiring the training of another model, and providing maps of activation values instead of true attribution scores. The adapted methods are evaluated on classification tasks for both real-valued and spiking data, and the accuracy of the proposed methods is confirmed through perturbation experiments at the pixel and spike levels.

Results and discussion

The results reveal that gradient-based SNN attribution methods successfully identify highly contributing pixels and spikes with significantly less computation time than model-agnostic methods. Additionally, we observe that the chosen coding technique has a noticeable effect on the input features that will be most significant. These findings demonstrate the potential of gradient-based explainability methods for SNNs in improving our understanding of how these networks process information and contribute to the development of more efficient and accurate SNNs.

From Brain Models to Robotic Embodied Cognition: How Does Biological Plausibility Inform Neuromorphic Systems?

We examine the challenging "marriage" between computational efficiency and biological plausibility-A crucial node in the domain of spiking neural networks at the intersection of neuroscience, artificial intelligence, and robotics. Through a transdisciplinary review, we retrace the historical and most recent constraining influences that these parallel fields have exerted on descriptive analysis of the brain, construction of predictive brain models, and ultimately, the embodiment of neural networks in an enacted robotic agent. We study models of Spiking Neural Networks (SNN) as the central means enabling autonomous and intelligent behaviors in biological systems. We then provide a critical comparison of the available hardware and software to emulate SNNs for investigating biological entities and their application on artificial systems. Neuromorphics is identified as a promising tool to embody SNNs in real physical systems and different neuromorphic chips are compared. The concepts required for describing SNNs are dissected and contextualized in the new no man's land between cognitive neuroscience and artificial intelligence. Although there are recent reviews on the application of neuromorphic computing in various modules of the guidance, navigation, and control of robotic systems, the focus of this paper is more on closing the cognition loop in SNN-embodied robotics. We argue that biologically viable spiking neuronal models used for electroencephalogram signals are excellent candidates for furthering our knowledge of the explainability of SNNs. We complete our survey by reviewing different robotic modules that can benefit from neuromorphic hardware, e.g., perception (with a focus on vision), localization, and cognition. We conclude that the tradeoff between symbolic computational power and biological plausibility of hardware can be best addressed by neuromorphics, whose presence in neurorobotics provides an accountable empirical testbench for investigating synthetic and natural embodied cognition. We argue this is where both theoretical and empirical future work should converge in multidisciplinary efforts involving neuroscience, artificial intelligence, and robotics.

Sensitivity analysis of point neuron model simulations implemented on neuromorphic hardware

With the ongoing growth in the field of neuro-inspired computing, newly arriving computational architectures demand extensive validation and testing against existing benchmarks to establish their competence and value. In our work, we break down the validation step into two parts-(1) establishing a methodological and numerical groundwork to establish a comparison between neuromorphic and conventional platforms and, (2) performing a sensitivity analysis on the obtained model regime to assess its robustness. We study the neuronal dynamics based on the Leaky Integrate and Fire (LIF) model, which is built upon data from the mouse visual cortex spanning a set of anatomical and physiological constraints. Intel Corp.'s first neuromorphic chip "Loihi" serves as our neuromorphic platform and results on it are validated against the classical simulations. After setting up a model that allows a seamless mapping between the Loihi and the classical simulations, we find that Loihi replicates classical simulations very efficiently with high precision. This model is then subjected to the second phase of validation, through sensitivity analysis, by assessing the impact on the cost function as values of the significant model parameters are varied. The work is done in two steps-(1) assessing the impact while changing one parameter at a time, (2) assessing the impact while changing two parameters at a time. We observe that the model is quite robust for majority of the parameters with slight change in the cost function. We also identify a subset of the model parameters changes which make the model more sensitive and thus, need to be defined more precisely.

Adaptive STDP-based on-chip spike pattern detection

A spiking neural network (SNN) is a bottom-up tool used to describe information processing in brain microcircuits. It is becoming a crucial neuromorphic computational model. Spike-timing-dependent plasticity (STDP) is an unsupervised brain-like learning rule implemented in many SNNs and neuromorphic chips. However, a significant performance gap exists between ideal model simulation and neuromorphic implementation. The performance of STDP learning in neuromorphic chips deteriorates because the resolution of synaptic efficacy in such chips is generally restricted to 6 bits or less, whereas simulations employ the entire 64-bit floating-point precision available on digital computers. Previously, we introduced a bio-inspired learning rule named adaptive STDP and demonstrated via numerical simulation that adaptive STDP (using only 4-bit fixed-point synaptic efficacy) performs similarly to STDP learning (using 64-bit floating-point precision) in a noisy spike pattern detection model. Herein, we present the experimental results demonstrating the performance of adaptive STDP learning. To the best of our knowledge, this is the first study that demonstrates unsupervised noisy spatiotemporal spike pattern detection to perform well and maintain the simulation performance on a mixed-signal CMOS neuromorphic chip with low-resolution synaptic efficacy. The chip was designed in Taiwan Semiconductor Manufacturing Company (TSMC) 250 nm CMOS technology node and comprises a soma circuit and 256 synapse circuits along with their learning circuitry.

Encoding integers and rationals on neuromorphic computers using virtual neuron

Neuromorphic computers emulate the human brain while being extremely power efficient for computing tasks. In fact, they are poised to be critical for energy-efficient computing in the future. Neuromorphic computers are primarily used in spiking neural network-based machine learning applications. However, they are known to be Turing-complete, and in theory can perform all general-purpose computation. One of the biggest bottlenecks in realizing general-purpose computations on neuromorphic computers today is the inability to efficiently encode data on the neuromorphic computers. To fully realize the potential of neuromorphic computers for energy-efficient general-purpose computing, efficient mechanisms must be devised for encoding numbers. Current encoding mechanisms (e.g., binning, rate-based encoding, and time-based encoding) have limited applicability and are not suited for general-purpose computation. In this paper, we present the virtual neuron abstraction as a mechanism for encoding and adding integers and rational numbers by using spiking neural network primitives. We evaluate the performance of the virtual neuron on physical and simulated neuromorphic hardware. We estimate that the virtual neuron could perform an addition operation using just 23 nJ of energy on average with a mixed-signal, memristor-based neuromorphic processor. We also demonstrate the utility of the virtual neuron by using it in some of the μ-recursive functions, which are the building blocks of general-purpose computation.

Oscillatory neural network learning for pattern recognition: an on-chip learning perspective and implementation

In the human brain, learning is continuous, while currently in AI, learning algorithms are pre-trained, making the model non-evolutive and predetermined. However, even in AI models, environment and input data change over time. Thus, there is a need to study continual learning algorithms. In particular, there is a need to investigate how to implement such continual learning algorithms on-chip. In this work, we focus on Oscillatory Neural Networks (ONNs), a neuromorphic computing paradigm performing auto-associative memory tasks, like Hopfield Neural Networks (HNNs). We study the adaptability of the HNN unsupervised learning rules to on-chip learning with ONN. In addition, we propose a first solution to implement unsupervised on-chip learning using a digital ONN design. We show that the architecture enables efficient ONN on-chip learning with Hebbian and Storkey learning rules in hundreds of microseconds for networks with up to 35 fully-connected digital oscillators.

Meta-SpikePropamine: learning to learn with synaptic plasticity in spiking neural networks

We propose that in order to harness our understanding of neuroscience toward machine learning, we must first have powerful tools for training brain-like models of learning. Although substantial progress has been made toward understanding the dynamics of learning in the brain, neuroscience-derived models of learning have yet to demonstrate the same performance capabilities as methods in deep learning such as gradient descent. Inspired by the successes of machine learning using gradient descent, we introduce a bi-level optimization framework that seeks to both solve online learning tasks and improve the ability to learn online using models of plasticity from neuroscience. We demonstrate that models of three-factor learning with synaptic plasticity taken from the neuroscience literature can be trained in Spiking Neural Networks (SNNs) with gradient descent via a framework of learning-to-learn to address challenging online learning problems. This framework opens a new path toward developing neuroscience inspired online learning algorithms.

Listen to the Brain-Auditory Sound Source Localization in Neuromorphic Computing Architectures

Conventional processing of sensory input often relies on uniform sampling leading to redundant information and unnecessary resource consumption throughout the entire processing pipeline. Neuromorphic computing challenges these conventions by mimicking biology and employing distributed event-based hardware. Based on the task of lateral auditory sound source localization (SSL), we propose a generic approach to map biologically inspired neural networks to neuromorphic hardware. First, we model the neural mechanisms of SSL based on the interaural level difference (ILD). Afterward, we identify generic computational motifs within the model and transform them into spike-based components. A hardware-specific step then implements them on neuromorphic hardware. We exemplify our approach by mapping the neural SSL model onto two platforms, namely the IBM TrueNorth Neurosynaptic System and SpiNNaker. Both implementations have been tested on synthetic and real-world data in terms of neural tunings and readout characteristics. For synthetic stimuli, both implementations provide a perfect readout (100% accuracy). Preliminary real-world experiments yield accuracies of 78% (TrueNorth) and 13% (SpiNNaker), RMSEs of 41∘ and 39∘, and MAEs of 18∘ and 29∘, respectively. Overall, the proposed mapping approach allows for the successful implementation of the same SSL model on two different neuromorphic architectures paving the way toward more hardware-independent neural SSL.

Variational learning of quantum ground states on spiking neuromorphic hardware

Recent research has demonstrated the usefulness of neural networks as variational ansatz functions for quantum many-body states. However, high-dimensional sampling spaces and transient autocorrelations confront these approaches with a challenging computational bottleneck. Compared to conventional neural networks, physical model devices offer a fast, efficient and inherently parallel substrate capable of related forms of Markov chain Monte Carlo sampling. Here, we demonstrate the ability of a neuromorphic chip to represent the ground states of quantum spin models by variational energy minimization. We develop a training algorithm and apply it to the transverse field Ising model, showing good performance at moderate system sizes (N≤10). A systematic hyperparameter study shows that performance depends on sample quality, which is limited by temporal parameter variations on the analog neuromorphic chip. Our work thus provides an important step towards harnessing the capabilities of neuromorphic hardware for tackling the curse of dimensionality in quantum many-body problems.

•

Variational scheme for representing quantum ground states with neuromorphic hardware

•

Accelerated physical system yields system-size independent sample generation time

•

Accurate learning of ground states across a quantum phase transition

•

Detailed analysis of algorithmic and technical limitations

A System-on-Chip Based Hybrid Neuromorphic Compute Node Architecture for Reproducible Hyper-Real-Time Simulations of Spiking Neural Networks

Despite the great strides neuroscience has made in recent decades, the underlying principles of brain function remain largely unknown. Advancing the field strongly depends on the ability to study large-scale neural networks and perform complex simulations. In this context, simulations in hyper-real-time are of high interest, as they would enable both comprehensive parameter scans and the study of slow processes, such as learning and long-term memory. Not even the fastest supercomputer available today is able to meet the challenge of accurate and reproducible simulation with hyper-real acceleration. The development of novel neuromorphic computer architectures holds out promise, but the high costs and long development cycles for application-specific hardware solutions makes it difficult to keep pace with the rapid developments in neuroscience. However, advances in System-on-Chip (SoC) device technology and tools are now providing interesting new design possibilities for application-specific implementations. Here, we present a novel hybrid software-hardware architecture approach for a neuromorphic compute node intended to work in a multi-node cluster configuration. The node design builds on the Xilinx Zynq-7000 SoC device architecture that combines a powerful programmable logic gate array (FPGA) and a dual-core ARM Cortex-A9 processor extension on a single chip. Our proposed architecture makes use of both and takes advantage of their tight coupling. We show that available SoC device technology can be used to build smaller neuromorphic computing clusters that enable hyper-real-time simulation of networks consisting of tens of thousands of neurons, and are thus capable of meeting the high demands for modeling and simulation in neuroscience.

Mapping and Validating a Point Neuron Model on Intel's Neuromorphic Hardware Loihi

Neuromorphic hardware is based on emulating the natural biological structure of the brain. Since its computational model is similar to standard neural models, it could serve as a computational accelerator for research projects in the field of neuroscience and artificial intelligence, including biomedical applications. However, in order to exploit this new generation of computer chips, we ought to perform rigorous simulation and consequent validation of neuromorphic models against their conventional implementations. In this work, we lay out the numeric groundwork to enable a comparison between neuromorphic and conventional platforms. "Loihi"-Intel's fifth generation neuromorphic chip, which is based on the idea of Spiking Neural Networks (SNNs) emulating the activity of neurons in the brain, serves as our neuromorphic platform. The work here focuses on Leaky Integrate and Fire (LIF) models based on neurons in the mouse primary visual cortex and matched to a rich data set of anatomical, physiological and behavioral constraints. Simulations on classical hardware serve as the validation platform for the neuromorphic implementation. We find that Loihi replicates classical simulations very efficiently with high precision. As a by-product, we also investigate Loihi's potential in terms of scalability and performance and find that it scales notably well in terms of run-time performance as the simulated networks become larger.

Mapping and Validating a Point Neuron Model on Intel's Neuromorphic Hardware Loihi

Neuromorphic hardware is based on emulating the natural biological structure of the brain. Since its computational model is similar to standard neural models, it could serve as a computational accelerator for research projects in the field of neuroscience and artificial intelligence, including biomedical applications. However, in order to exploit this new generation of computer chips, we ought to perform rigorous simulation and consequent validation of neuromorphic models against their conventional implementations. In this work, we lay out the numeric groundwork to enable a comparison between neuromorphic and conventional platforms. "Loihi"-Intel's fifth generation neuromorphic chip, which is based on the idea of Spiking Neural Networks (SNNs) emulating the activity of neurons in the brain, serves as our neuromorphic platform. The work here focuses on Leaky Integrate and Fire (LIF) models based on neurons in the mouse primary visual cortex and matched to a rich data set of anatomical, physiological and behavioral constraints. Simulations on classical hardware serve as the validation platform for the neuromorphic implementation. We find that Loihi replicates classical simulations very efficiently with high precision. As a by-product, we also investigate Loihi's potential in terms of scalability and performance and find that it scales notably well in terms of run-time performance as the simulated networks become larger.

A Scalable Approach to Modeling on Accelerated Neuromorphic Hardware

Neuromorphic systems open up opportunities to enlarge the explorative space for computational research. However, it is often challenging to unite efficiency and usability. This work presents the software aspects of this endeavor for the BrainScaleS-2 system, a hybrid accelerated neuromorphic hardware architecture based on physical modeling. We introduce key aspects of the BrainScaleS-2 Operating System: experiment workflow, API layering, software design, and platform operation. We present use cases to discuss and derive requirements for the software and showcase the implementation. The focus lies on novel system and software features such as multi-compartmental neurons, fast re-configuration for hardware-in-the-loop training, applications for the embedded processors, the non-spiking operation mode, interactive platform access, and sustainable hardware/software co-development. Finally, we discuss further developments in terms of hardware scale-up, system usability, and efficiency.