Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks

Monitoring of Lake Ice Phenology Changes in Bosten Lake Based on Bayesian Change Detection Algorithm and Passive Microwave Remote Sensing (PMRS) Data

Lake ice phenology (LIP), hiding information about lake energy and material exchange, serves as an important indicator of climate change. Utilizing an efficient technique to swiftly extract lake ice information is crucial in the field of lake ice research. The Bayesian ensemble change detection (BECD) algorithm stands out as a powerful tool, requiring no threshold compared to other algorithms and, instead, utilizing the probability of abrupt changes to detect positions. This method is predominantly employed by automatically extracting change points from time series data, showcasing its efficiency and accuracy, especially in revealing phenological and seasonal characteristics. This paper focuses on Bosten Lake (BL) and employs PMRS data in conjunction with the Bayesian change detection algorithm. It introduces an automated method for extracting LIP information based on the Bayesian change detection algorithm. In this study, the BECD algorithm was employed to extract lake ice phenology information from passive microwave remote sensing data on Bosten Lake. The reliability of the passive microwave remote sensing data was further investigated through cross-validation with MOD10A1 data. Additionally, the Mann-Kendall non-parametric test was applied to analyze the trends in lake ice phenology changes in Bosten Lake. Spatial variations were examined using MOD09GQ data. The results indicate: (1) The Bayesian change detection algorithm (BCDA), in conjunction with PMRS data, offers a high level of accuracy and reliability in extracting the lake ice freezing and thawing processes. It accurately captures the phenological parameters of BL's ice. (2) The average start date of lake ice freezing is in mid-December, lasting for about three months, and the start date of ice thawing is usually in mid-March. The freezing duration (FD) of lake ice is relatively short, shortening each year, while the thawing speed is faster. The stability of the lake ice complete ice cover duration is poor, averaging 84 days. (3) The dynamic evolution of BL ice is rapid and regionally distinct, with the lake center, southwest, and southeast regions being the earliest areas for ice formation and thawing, while the northwest coastal and Huang Shui Gou areas experience later ice formation. (4) Since 1978, BL's ice has exhibited noticeable trends: the onset of freezing, the commencement of thawing, complete thawing, and full freezing have progressively advanced in regard to dates. The periods of full ice coverage, ice presence, thawing, and freezing have all shown a tendency toward shorter durations. This study introduces an innovative method for LIP extraction, opening up new prospects for the study of lake ecosystem and strategy formulation, which is worthy of further exploration and application in other lakes and regions.

Monitoring time domain characteristics of Parkinson's disease using 3D memristive neuromorphic system

Introduction

Parkinson's disease (PD) is a neurodegenerative disorder affecting millions of patients. Closed-Loop Deep Brain Stimulation (CL-DBS) is a therapy that can alleviate the symptoms of PD. The CL-DBS system consists of an electrode sending electrical stimulation signals to a specific region of the brain and a battery-powered stimulator implanted in the chest. The electrical stimuli in CL-DBS systems need to be adjusted in real-time in accordance with the state of PD symptoms. Therefore, fast and precise monitoring of PD symptoms is a critical function for CL-DBS systems. However, the current CL-DBS techniques suffer from high computational demands for real-time PD symptom monitoring, which are not feasible for implanted and wearable medical devices.

Methods

In this paper, we present an energy-efficient neuromorphic PD symptom detector using memristive three-dimensional integrated circuits (3D-ICs). The excessive oscillation at beta frequencies (13-35 Hz) at the subthalamic nucleus (STN) is used as a biomarker of PD symptoms.

Results

Simulation results demonstrate that our neuromorphic PD detector, implemented with an 8-layer spiking Long Short-Term Memory (S-LSTM), excels in recognizing PD symptoms, achieving a training accuracy of 99.74% and a validation accuracy of 99.52% for a 75%-25% data split. Furthermore, we evaluated the improvement of our neuromorphic CL-DBS detector using NeuroSIM. The chip area, latency, energy, and power consumption of our CL-DBS detector were reduced by 47.4%, 66.63%, 65.6%, and 67.5%, respectively, for monolithic 3D-ICs. Similarly, for heterogeneous 3D-ICs, employing memristive synapses to replace traditional Static Random Access Memory (SRAM) resulted in reductions of 44.8%, 64.75%, 65.28%, and 67.7% in chip area, latency, and power usage.

Discussion

This study introduces a novel approach for PD symptom evaluation by directly utilizing spiking signals from neural activities in the time domain. This method significantly reduces the time and energy required for signal conversion compared to traditional frequency domain approaches. The study pioneers the use of neuromorphic computing and memristors in designing CL-DBS systems, surpassing SRAM-based designs in chip design area, latency, and energy efficiency. Lastly, the proposed neuromorphic PD detector demonstrates high resilience to timing variations in brain neural signals, as confirmed by robustness analysis.

Neuromorphic applications in medicine

In recent years, there has been a growing demand for miniaturization, low power consumption, quick treatments, and non-invasive clinical strategies in the healthcare industry. To meet these demands, healthcare professionals are seeking new technological paradigms that can improve diagnostic accuracy while ensuring patient compliance. Neuromorphic engineering, which uses neural models in hardware and software to replicate brain-like behaviors, can help usher in a new era of medicine by delivering low power, low latency, small footprint, and high bandwidth solutions. This paper provides an overview of recent neuromorphic advancements in medicine, including medical imaging and cancer diagnosis, processing of biosignals for diagnosis, and biomedical interfaces, such as motor, cognitive, and perception prostheses. For each section, we provide examples of how brain-inspired models can successfully compete with conventional artificial intelligence algorithms, demonstrating the potential of neuromorphic engineering to meet demands and improve patient outcomes. Lastly, we discuss current struggles in fitting neuromorphic hardware with non-neuromorphic technologies and propose potential solutions for future bottlenecks in hardware compatibility.

The computational power of the human brain

At the end of the 20th century, analog systems in computer science have been widely replaced by digital systems due to their higher computing power. Nevertheless, the question keeps being intriguing until now: is the brain analog or digital? Initially, the latter has been favored, considering it as a Turing machine that works like a digital computer. However, more recently, digital and analog processes have been combined to implant human behavior in robots, endowing them with artificial intelligence (AI). Therefore, we think it is timely to compare mathematical models with the biology of computation in the brain. To this end, digital and analog processes clearly identified in cellular and molecular interactions in the Central Nervous System are highlighted. But above that, we try to pinpoint reasons distinguishing in silico computation from salient features of biological computation. First, genuinely analog information processing has been observed in electrical synapses and through gap junctions, the latter both in neurons and astrocytes. Apparently opposed to that, neuronal action potentials (APs) or spikes represent clearly digital events, like the yes/no or 1/0 of a Turing machine. However, spikes are rarely uniform, but can vary in amplitude and widths, which has significant, differential effects on transmitter release at the presynaptic terminal, where notwithstanding the quantal (vesicular) release itself is digital. Conversely, at the dendritic site of the postsynaptic neuron, there are numerous analog events of computation. Moreover, synaptic transmission of information is not only neuronal, but heavily influenced by astrocytes tightly ensheathing the majority of synapses in brain (tripartite synapse). At least at this point, LTP and LTD modifying synaptic plasticity and believed to induce short and long-term memory processes including consolidation (equivalent to RAM and ROM in electronic devices) have to be discussed. The present knowledge of how the brain stores and retrieves memories includes a variety of options (e.g., neuronal network oscillations, engram cells, astrocytic syncytium). Also epigenetic features play crucial roles in memory formation and its consolidation, which necessarily guides to molecular events like gene transcription and translation. In conclusion, brain computation is not only digital or analog, or a combination of both, but encompasses features in parallel, and of higher orders of complexity.

A Co-Designed Neuromorphic Chip With Compact (17.9K F2) and Weak Neuron Number-Dependent Neuron/Synapse Modules

Many efforts have been made to improve the neuron integration efficiency on neuromorphic chips, such as using emerging memory devices and shrinking CMOS technology nodes. However, in the fully connected (FC) neuromorphic core, increasing the number of neurons will lead to a square increase in synapse & dendrite costs and a high-slope linear increase in soma costs, resulting in an explosive growth of core hardware costs. We propose a co-designed neuromorphic core (SRCcore) based on the quantized spiking neural network (SNN) technology and compact chip design methodology. The cost of the neuron/synapse module in SRCcore weakly depends on the neuron number, which effectively relieves the growth pressure of the core area caused by increasing the neuron number. In the proposed BICS chip based on SRCcore, although the neuron/synapse module implements 1∼16 times of neurons and 1∼66 times of synapses, it only costs an area of 1.79 × 10⁷ F², which is 7.9%∼38.6% of that in previous works. Based on the weight quantization strategy matched with SRCcore, quantized SNNs achieve 0.05%∼2.19% higher accuracy than previous works, thus supporting the design and application of SRCcore. Finally, a cross-modeling application is demonstrated based on the chip. We hope this work will accelerate the development of cortical-scale neuromorphic systems.

Advancements in Algorithms and Neuromorphic Hardware for Spiking Neural Networks

Artificial neural networks (ANNs) have experienced a rapid advancement for their success in various application domains, including autonomous driving and drone vision. Researchers have been improving the performance efficiency and computational requirement of ANNs inspired by the mechanisms of the biological brain. Spiking neural networks (SNNs) provide a power-efficient and brain-inspired computing paradigm for machine learning applications. However, evaluating large-scale SNNs on classical von Neumann architectures (central processing units/graphics processing units) demands a high amount of power and time. Therefore, hardware designers have developed neuromorphic platforms to execute SNNs in and approach that combines fast processing and low power consumption. Recently, field-programmable gate arrays (FPGAs) have been considered promising candidates for implementing neuromorphic solutions due to their varied advantages, such as higher flexibility, shorter design, and excellent stability. This review aims to describe recent advances in SNNs and the neuromorphic hardware platforms (digital, analog, hybrid, and FPGA based) suitable for their implementation. We present that biological background of SNN learning, such as neuron models and information encoding techniques, followed by a categorization of SNN training. In addition, we describe state-of-the-art SNN simulators. Furthermore, we review and present FPGA-based hardware implementation of SNNs. Finally, we discuss some future directions for research in this field.

ABO3 multiferroic perovskite materials for memristive memory and neuromorphic computing

The unique electron spin, transfer, polarization and magnetoelectric coupling characteristics of ABO₃ multiferroic perovskite materials make them promising candidates for application in multifunctional nanoelectronic devices. Reversible ferroelectric polarization, controllable defect concentration and domain wall movement originated from the ABO₃ multiferroic perovskite materials promotes its memristive effect, which further highlights data storage, information processing and neuromorphic computing in diverse artificial intelligence applications. In particular, ion doping, electrode selection, and interface modulation have been demonstrated in ABO₃-based memristive devices for ultrahigh data storage, ultrafast information processing, and efficient neuromorphic computing. These approaches presented today including controlling the dopant in the active layer, altering the oxygen vacancy distribution, modulating the diffusion depth of ions, and constructing the interface-dependent band structure were believed to be efficient methods for obtaining unique resistive switching (RS) behavior for various applications. In this review, internal physical dynamics, preparation technologies, and modulation methods are systemically examined as well as the progress, challenges, and possible solutions are proposed for next generation emerging ABO₃-based memristive application in artificial intelligence.

Bienenstock-Cooper-Munro Learning Rule Realized in Polysaccharide-Gated Synaptic Transistors with Tunable Threshold

With reference to the organization of the human brain nervous system, a hardware-based approach that builds massively parallel neuromorphic circuits is of great significance to neuromorphic computing. The Bienenstock-Cooper-Munro (BCM) learning rule, which describes that the synaptic weight modulation exhibits frequency-dependent and tunable frequency threshold characteristics, is more compatible with the working principle of neuromorphic computing systems than spike-timing-dependent plasticity. Therefore, it is interesting to simulate the BCM learning rule on solid-state synaptic devices. Here, we have prepared λ-carrageenan (λ-car) electrolyte-gated oxide synaptic transistors, which exhibit good transistor performances, including a low subthreshold swing of 125 mV/dec, an on/off ratio larger than 10⁶, and a mobility of 9.5 cm² V^-1 s^-1. By modulating the initial channel current and spike frequency, the simulation of the BCM rule was successfully realized. The competitive relationship between the drift of protons under an electric field and the spontaneous diffusion of protons can explain this mechanism. The proposed λ-car-gated synaptic transistor has a great significance to neuromorphic computing.

Initializing photonic feed-forward neural networks using auxiliary tasks

Photonics is among the most promising emerging technologies for providing fast and energy-efficient Deep Learning (DL) implementations. Despite their advantages, these photonic DL accelerators also come with certain important limitations. For example, the majority of existing photonic accelerators do not currently support many of the activation functions that are commonly used in DL, such as the ReLU activation function. Instead, sinusoidal and sigmoidal nonlinearities are usually employed, rendering the training process unstable and difficult to tune, mainly due to vanishing gradient phenomena. Thus, photonic DL models usually require carefully fine-tuning all their training hyper-parameters in order to ensure that the training process will proceed smoothly. Despite the recent advances in initialization schemes, as well as in optimization algorithms, training photonic DL models is still especially challenging. To overcome these limitations, we propose a novel adaptive initialization method that employs auxiliary tasks to estimate the optimal initialization variance for each layer of a network. The effectiveness of the proposed approach is demonstrated using two different datasets, as well as two recently proposed photonic activation functions and three different initialization methods. Apart from significantly increasing the stability of the training process, the proposed method can be directly used with any photonic activation function, without further requiring any other kind of fine-tuning, as also demonstrated through the conducted experiments.

Training memristor-based multilayer neuromorphic networks with SGD, momentum and adaptive learning rates

Neural networks implemented with traditional hardware face inherent limitation of memory latency. Specifically, the processing units like GPUs, FPGAs, and customized ASICs, must wait for inputs to read from memory and outputs to write back. This motivates memristor-based neuromorphic computing in which the memory units (i.e., memristors) have computing capabilities. However, training a memristor-based neural network is difficult since memristors work differently from CMOS hardware. This paper proposes a new training approach that enables prevailing neural network training techniques to be applied for memristor-based neuromorphic networks. Particularly, we introduce momentum and adaptive learning rate to the circuit training, both of which are proven methods that significantly accelerate the convergence of neural network parameters. Furthermore, we show that this circuit can be used for neural networks with arbitrary numbers of layers, neurons, and parameters. Simulation results on four classification tasks demonstrate that the proposed circuit achieves both high accuracy and fast speed. Compared with the SGD-based training circuit, on the WBC data set, the training speed of our circuit is increased by 37.2% while the accuracy is only reduced by 0.77%. On the MNIST data set, the new circuit even leads to improved accuracy.

Memristive and Synaptic Characteristics of Nitride-Based Heterostructures on Si Substrate

Brain-inspired artificial synaptic devices and neurons have the potential for application in future neuromorphic computing as they consume low energy. In this study, the memristive switching characteristics of a nitride-based device with two amorphous layers (SiN/BN) is investigated. We demonstrate the coexistence of filamentary (abrupt) and interface (homogeneous) switching of Ni/SiN/BN/n⁺⁺-Si devices. A better gradual conductance modulation is achieved for interface-type switching as compared with filamentary switching for an artificial synaptic device using appropriate voltage pulse stimulations. The improved classification accuracy for the interface switching (85.6%) is confirmed and compared to the accuracy of the filamentary switching mode (75.1%) by a three-layer neural network (784 × 128 × 10). Furthermore, the spike-timing-dependent plasticity characteristics of the synaptic device are also demonstrated. The results indicate the possibility of achieving an artificial synapse with a bilayer SiN/BN structure.

Task-Independent Spiking Central Pattern Generator: A Learning-Based Approach

Legged locomotion is a challenging task in the field of robotics but a rather simple one in nature. This motivates the use of biological methodologies as solutions to this problem. Central pattern generators are neural networks that are thought to be responsible for locomotion in humans and some animal species. As for robotics, many attempts were made to reproduce such systems and use them for a similar goal. One interesting design model is based on spiking neural networks. This model is the main focus of this work, as its contribution is not limited to engineering but also applicable to neuroscience. This paper introduces a new general framework for building central pattern generators that are task-independent, biologically plausible, and rely on learning methods. The abilities and properties of the presented approach are not only evaluated in simulation but also in a robotic experiment. The results are very promising as the used robot was able to perform stable walking at different speeds and to change speed within the same gait cycle.

Threshold-Tunable, Spike-Rate-Dependent Plasticity Originating from Interfacial Proton Gating for Pattern Learning and Memory

Recently, neuromorphic devices have been receiving increasing interest in the field of artificial intelligence (AI). Realization of fundamental synaptic plasticities on hard-ware devices would endow new intensions for neuromorphic devices. Spike-rate-dependent plasticity (SRDP) is one of the most important synaptic learning mechanisms in brain cognitive behaviors. It is thus interesting to mimic the SRDP behaviors on solid-state neuromorphic devices. In the present work, nanogranular phosphorus silicate glass (PSG)-based proton conductive electrolyte-gated oxide neuromorphic transistors have been proposed. The oxide neuromorphic transistors have good transistor performances and frequency-dependent synaptic plasticity behavior. Moreover, the neuromorphic transistor exhibits SRDP activities. Interestingly, by introducing priming synaptic stimuli, the modulation of threshold frequency value distinguishing synaptic potentiation from synaptic depression is realized for the first time on an electrolyte-gated neuromorphic transistor. Such a mechanism can be well understood with interfacial proton gating effects of the nanogranular PSG-based electrolyte. Furthermore, the effects of SRDP learning rules on pattern learning and memory behaviors have been conceptually demonstrated. The proposed neuromorphic transistors have potential applications in neuromorphic engineering.

Electronic Skin: Recent Progress and Future Prospects for Skin-Attachable Devices for Health Monitoring, Robotics, and Prosthetics

Recent progress in electronic skin or e-skin research is broadly reviewed, focusing on technologies needed in three main applications: skin-attachable electronics, robotics, and prosthetics. First, since e-skin will be exposed to prolonged stresses of various kinds and needs to be conformally adhered to irregularly shaped surfaces, materials with intrinsic stretchability and self-healing properties are of great importance. Second, tactile sensing capability such as the detection of pressure, strain, slip, force vector, and temperature are important for health monitoring in skin attachable devices, and to enable object manipulation and detection of surrounding environment for robotics and prosthetics. For skin attachable devices, chemical and electrophysiological sensing and wireless signal communication are of high significance to fully gauge the state of health of users and to ensure user comfort. For robotics and prosthetics, large-area integration on 3D surfaces in a facile and scalable manner is critical. Furthermore, new signal processing strategies using neuromorphic devices are needed to efficiently process tactile information in a parallel and low power manner. For prosthetics, neural interfacing electrodes are of high importance. These topics are discussed, focusing on progress, current challenges, and future prospects.

On the accuracy and computational cost of spiking neuron implementation

Since more than a decade ago, three statements about spiking neuron (SN) implementations have been widely accepted: 1) Hodgkin and Huxley (HH) model is computationally prohibitive, 2) Izhikevich (IZH) artificial neuron is as efficient as Leaky Integrate-and-Fire (LIF) model, and 3) IZH model is more efficient than HH model (Izhikevich, 2004). As suggested by Hodgkin and Huxley (1952), their model operates in two modes: by using the α's and β's rate functions directly (HH model) and by storing them into tables (HHT model) for computational cost reduction. Recently, it has been stated that: 1) HHT model (HH using tables) is not prohibitive, 2) IZH model is not efficient, and 3) both HHT and IZH models are comparable in computational cost (Skocik & Long, 2014). That controversy shows that there is no consensus concerning SN simulation capacities. Hence, in this work, we introduce a refined approach, based on the multiobjective optimization theory, describing the SN simulation capacities and ultimately choosing optimal simulation parameters. We have used normalized metrics to define the capacity levels of accuracy, computational cost, and efficiency. Normalized metrics allowed comparisons between SNs at the same level or scale. We conducted tests for balanced, lower, and upper boundary conditions under a regular spiking mode with constant and random current stimuli. We found optimal simulation parameters leading to a balance between computational cost and accuracy. Importantly, and, in general, we found that 1) HH model (without using tables) is the most accurate, computationally inexpensive, and efficient, 2) IZH model is the most expensive and inefficient, 3) both LIF and HHT models are the most inaccurate, 4) HHT model is more expensive and inaccurate than HH model due to α's and β's table discretization, and 5) HHT model is not comparable in computational cost to IZH model. These results refute the theory formulated over a decade ago (Izhikevich, 2004) and go more in-depth in the statements formulated by Skocik and Long (2014). Our statements imply that the number of dimensions or FLOPS in the SNs are theoretical but not practical indicators of the true computational cost. The metric we propose for the computational cost is more precise than FLOPS and was found to be invariant to computer architecture. Moreover, we found that the firing frequency used in previous works is a necessary but an insufficient metric to evaluate the simulation accuracy. We also show that our results are consistent with the theory of numerical methods and the theory of SN discontinuity. Discontinuous SNs, such LIF and IZH models, introduce a considerable error every time a spike is generated. In addition, compared to the constant input current, the random input current increases the computational cost and inaccuracy. Besides, we found that the search for optimal simulation parameters is problem-specific. That is important because most of the previous works have intended to find a general and unique optimal simulation. Here, we show that this solution could not exist because it is a multiobjective optimization problem that depends on several factors. This work sets up a renewed thesis concerning the SN simulation that is useful to several related research areas, including the emergent Deep Spiking Neural Networks.

Memristor Neural Network Training with Clock Synchronous Neuromorphic System

Memristor devices are considered to have the potential to implement unsupervised learning, especially spike timing-dependent plasticity (STDP), in the field of neuromorphic hardware research. In this study, a neuromorphic hardware system for multilayer unsupervised learning was designed, and unsupervised learning was performed with a memristor neural network. We showed that the nonlinear characteristic memristor neural network can be trained by unsupervised learning only with the correlation between inputs and outputs. Moreover, a method to train nonlinear memristor devices in a supervised manner, named guide training, was devised. Memristor devices have a nonlinear characteristic, which makes implementing machine learning algorithms, such as backpropagation, difficult. The guide-training algorithm devised in this paper updates the synaptic weights by only using the correlations between inputs and outputs, and therefore, neither complex mathematical formulas nor computations are required during the training. Thus, it is considered appropriate to train a nonlinear memristor neural network. All training and inference simulations were performed using the designed neuromorphic hardware system. With the system and memristor neural network, the image classification was successfully done using both the Hebbian unsupervised training and guide supervised training methods.

Memristor in a Reservoir System-Experimental Evidence for High-Level Computing and Neuromorphic Behavior of PbI2

Lead halides in an asymmetric layered structure form memristive devices which are controlled by the electronic structure of the PbX₂|metal interface. In this paper, we explain the mechanism that stands behind the I- V pinched hysteresis loop of the device and shortly present its synaptic-like plasticity (spike-timing-dependent plasticity and spike-rate-dependent plasticity) and nonvolatile memory effects. This memristive element was incorporated into a reservoir system, in particular, the echo-state network with delayed feedback, which exhibits brain-like recurrent behavior and demonstrates metaplasticity as one of the available learning mechanisms. It can serve as a classification system that classifies input signals according to their amplitude.

Recent advances in physical reservoir computing: A review

Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir. The reservoir is fixed and only the readout is trained with a simple method such as linear regression and classification. Thus, the major advantage of reservoir computing compared to other recurrent neural networks is fast learning, resulting in low training cost. Another advantage is that the reservoir without adaptive updating is amenable to hardware implementation using a variety of physical systems, substrates, and devices. In fact, such physical reservoir computing has attracted increasing attention in diverse fields of research. The purpose of this review is to provide an overview of recent advances in physical reservoir computing by classifying them according to the type of the reservoir. We discuss the current issues and perspectives related to physical reservoir computing, in order to further expand its practical applications and develop next-generation machine learning systems.

Classification and regression of spatio-temporal signals using NeuCube and its realization on SpiNNaker neuromorphic hardware

OBJECTIVE

The objective of this work is to use the capability of spiking neural networks to capture the spatio-temporal information encoded in time-series signals and decode them without the use of hand-crafted features and vector-based learning and the realization of the spiking model on low-power neuromorphic hardware.

APPROACH

The NeuCube spiking model was used to classify different grasp movements directly from raw surface electromyography signals (sEMG), the estimations of the applied finger forces as well as the classification of two motor imagery movements from raw electroencephalography (EEG). In a parallel investigation, the designed spiking decoder was implemented on SpiNNaker neuromorphic hardware, which allows low-energy real-time processing.

MAIN RESULTS

Experimental results reveal a better classification accuracy using the NeuCube model compared to traditional machine learning methods. For sEMG classification, we reached a training accuracy of 85% and a test accuracy of 84.8%, as well as less than 19% of relative root mean square error (rRMSE) when estimating finger forces from six subjects. For the EEG classification, a mean accuracy of 75% was obtained when tested on raw EEG data from nine subjects from the existing 2b dataset from 'BCI competition IV'.

SIGNIFICANCE

This work provides a proof of concept for a successful implementation of the NeuCube spiking model on the SpiNNaker neuromorphic platform for raw sEMG and EEG decoding, which could chart a route ahead for a new generation of portable closed-loop and low-power neuroprostheses.

Large-Scale Neuromorphic Spiking Array Processors: A Quest to Mimic the Brain

Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems. The brain has evolved over billions of years to solve difficult engineering problems by using efficient, parallel, low-power computation. The goal of NE is to design systems capable of brain-like computation. Numerous large-scale neuromorphic projects have emerged recently. This interdisciplinary field was listed among the top 10 technology breakthroughs of 2014 by the MIT Technology Review and among the top 10 emerging technologies of 2015 by the World Economic Forum. NE has two-way goals: one, a scientific goal to understand the computational properties of biological neural systems by using models implemented in integrated circuits (ICs); second, an engineering goal to exploit the known properties of biological systems to design and implement efficient devices for engineering applications. Building hardware neural emulators can be extremely useful for simulating large-scale neural models to explain how intelligent behavior arises in the brain. The principal advantages of neuromorphic emulators are that they are highly energy efficient, parallel and distributed, and require a small silicon area. Thus, compared to conventional CPUs, these neuromorphic emulators are beneficial in many engineering applications such as for the porting of deep learning algorithms for various recognitions tasks. In this review article, we describe some of the most significant neuromorphic spiking emulators, compare the different architectures and approaches used by them, illustrate their advantages and drawbacks, and highlight the capabilities that each can deliver to neural modelers. This article focuses on the discussion of large-scale emulators and is a continuation of a previous review of various neural and synapse circuits (Indiveri et al., 2011). We also explore applications where these emulators have been used and discuss some of their promising future applications.

Behavioral Learning in a Cognitive Neuromorphic Robot: An Integrative Approach

We present here a learning system using the iCub humanoid robot and the SpiNNaker neuromorphic chip to solve the real-world task of object-specific attention. Integrating spiking neural networks with robots introduces considerable complexity for questionable benefit if the objective is simply task performance. But, we suggest, in a cognitive robotics context, where the goal is understanding how to compute, such an approach may yield useful insights to neural architecture as well as learned behavior, especially if dedicated neural hardware is available. Recent advances in cognitive robotics and neuromorphic processing now make such systems possible. Using a scalable, structured, modular approach, we build a spiking neural network where the effects and impact of learning can be predicted and tested, and the network can be scaled or extended to new tasks automatically. We introduce several enhancements to a basic network and show how they can be used to direct performance toward behaviorally relevant goals. Results show that using a simple classical spike-timing-dependent plasticity (STDP) rule on selected connections, we can get the robot (and network) to progress from poor task-specific performance to good performance. Behaviorally relevant STDP appears to contribute strongly to positive learning: "do this" but less to negative learning: "don't do that." In addition, we observe that the effect of structural enhancements tends to be cumulative. The overall system suggests that it is by being able to exploit combinations of effects, rather than any one effect or property in isolation, that spiking networks can achieve compelling, task-relevant behavior.

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks

Biological intelligence processes information using impulses or spikes, which makes those living creatures able to perceive and act in the real world exceptionally well and outperform state-of-the-art robots in almost every aspect of life. To make up the deficit, emerging hardware technologies and software knowledge in the fields of neuroscience, electronics, and computer science have made it possible to design biologically realistic robots controlled by spiking neural networks (SNNs), inspired by the mechanism of brains. However, a comprehensive review on controlling robots based on SNNs is still missing. In this paper, we survey the developments of the past decade in the field of spiking neural networks for control tasks, with particular focus on the fast emerging robotics-related applications. We first highlight the primary impetuses of SNN-based robotics tasks in terms of speed, energy efficiency, and computation capabilities. We then classify those SNN-based robotic applications according to different learning rules and explicate those learning rules with their corresponding robotic applications. We also briefly present some existing platforms that offer an interaction between SNNs and robotics simulations for exploration and exploitation. Finally, we conclude our survey with a forecast of future challenges and some associated potential research topics in terms of controlling robots based on SNNs.

Unsupervised heart-rate estimation in wearables with Liquid states and a probabilistic readout

Heart-rate estimation is a fundamental feature of modern wearable devices. In this paper we propose a machine learning technique to estimate heart-rate from electrocardiogram (ECG) data collected using wearable devices. The novelty of our approach lies in (1) encoding spatio-temporal properties of ECG signals directly into spike train and using this to excite recurrently connected spiking neurons in a Liquid State Machine computation model; (2) a novel learning algorithm; and (3) an intelligently designed unsupervised readout based on Fuzzy c-Means clustering of spike responses from a subset of neurons (Liquid states), selected using particle swarm optimization. Our approach differs from existing works by learning directly from ECG signals (allowing personalization), without requiring costly data annotations. Additionally, our approach can be easily implemented on state-of-the-art spiking-based neuromorphic systems, offering high accuracy, yet significantly low energy footprint, leading to an extended battery-life of wearable devices. We validated our approach with CARLsim, a GPU accelerated spiking neural network simulator modeling Izhikevich spiking neurons with Spike Timing Dependent Plasticity (STDP) and homeostatic scaling. A range of subjects is considered from in-house clinical trials and public ECG databases. Results show high accuracy and low energy footprint in heart-rate estimation across subjects with and without cardiac irregularities, signifying the strong potential of this approach to be integrated in future wearable devices.

The Human Brain Project: Creating a European Research Infrastructure to Decode the Human Brain

Decoding the human brain is perhaps the most fascinating scientific challenge in the 21st century. The Human Brain Project (HBP), a 10-year European Flagship, targets the reconstruction of the brain's multi-scale organization. It uses productive loops of experiments, medical, data, data analytics, and simulation on all levels that will eventually bridge the scales. The HBP IT architecture is unique, utilizing cloud-based collaboration and development platforms with databases, workflow systems, petabyte storage, and supercomputers. The HBP is developing toward a European research infrastructure advancing brain research, medicine, and brain-inspired information technology.

Neuromorphic neural interfaces: from neurophysiological inspiration to biohybrid coupling with nervous systems

OBJECTIVE

Computation in nervous systems operates with different computational primitives, and on different hardware, than traditional digital computation and is thus subjected to different constraints from its digital counterpart regarding the use of physical resources such as time, space and energy. In an effort to better understand neural computation on a physical medium with similar spatiotemporal and energetic constraints, the field of neuromorphic engineering aims to design and implement electronic systems that emulate in very large-scale integration (VLSI) hardware the organization and functions of neural systems at multiple levels of biological organization, from individual neurons up to large circuits and networks. Mixed analog/digital neuromorphic VLSI systems are compact, consume little power and operate in real time independently of the size and complexity of the model.

APPROACH

This article highlights the current efforts to interface neuromorphic systems with neural systems at multiple levels of biological organization, from the synaptic to the system level, and discusses the prospects for future biohybrid systems with neuromorphic circuits of greater complexity.

MAIN RESULTS

Single silicon neurons have been interfaced successfully with invertebrate and vertebrate neural networks. This approach allowed the investigation of neural properties that are inaccessible with traditional techniques while providing a realistic biological context not achievable with traditional numerical modeling methods. At the network level, populations of neurons are envisioned to communicate bidirectionally with neuromorphic processors of hundreds or thousands of silicon neurons. Recent work on brain-machine interfaces suggests that this is feasible with current neuromorphic technology.

SIGNIFICANCE

Biohybrid interfaces between biological neurons and VLSI neuromorphic systems of varying complexity have started to emerge in the literature. Primarily intended as a computational tool for investigating fundamental questions related to neural dynamics, the sophistication of current neuromorphic systems now allows direct interfaces with large neuronal networks and circuits, resulting in potentially interesting clinical applications for neuroengineering systems, neuroprosthetics and neurorehabilitation.