Optimization methods for spiking neurons and networks

Molecular Toxicity Virtual Screening Applying a Quantized Computational SNN-Based Framework

Spiking neural networks are biologically inspired machine learning algorithms attracting researchers' attention for their applicability to alternative energy-efficient hardware other than traditional computers. In the current work, spiking neural networks have been tested in a quantitative structure-activity analysis targeting the toxicity of molecules. Multiple public-domain databases of compounds have been evaluated with spiking neural networks, achieving accuracies compatible with high-quality frameworks presented in the previous literature. The numerical experiments also included an analysis of hyperparameters and tested the spiking neural networks on molecular fingerprints of different lengths. Proposing alternatives to traditional software and hardware for time- and resource-consuming tasks, such as those found in chemoinformatics, may open the door to new research and improvements in the field.

Parameter Estimation of Two Spiking Neuron Models With Meta-Heuristic Optimization Algorithms

The automatic fitting of spiking neuron models to experimental data is a challenging problem. The integrate and fire model and Hodgkin–Huxley (HH) models represent the two complexity extremes of spiking neural models. Between these two extremes lies two and three differential-equation-based models. In this work, we investigate the problem of parameter estimation of two simple neuron models with a sharp reset in order to fit the spike timing of electro-physiological recordings based on two problem formulations. Five optimization algorithms are investigated; three of them have not been used to tackle this problem before. The new algorithms show improved fitting when compared with the old ones in both problems under investigation. The improvement in fitness function is between 5 and 8%, which is achieved by using the new algorithms while also being more consistent between independent trials. Furthermore, a new problem formulation is investigated that uses a lower number of search space variables when compared to the ones reported in related literature.

EvAn: Neuromorphic Event-Based Sparse Anomaly Detection

Event-based cameras are bio-inspired novel sensors that asynchronously record changes in illumination in the form of events. This principle results in significant advantages over conventional cameras, such as low power utilization, high dynamic range, and no motion blur. Moreover, by design, such cameras encode only the relative motion between the scene and the sensor and not the static background to yield a very sparse data structure. In this paper, we leverage these advantages of an event camera toward a critical vision application-video anomaly detection. We propose an anomaly detection solution in the event domain with a conditional Generative Adversarial Network (cGAN) made up of sparse submanifold convolution layers. Video analytics tasks such as anomaly detection depend on the motion history at each pixel. To enable this, we also put forward a generic unsupervised deep learning solution to learn a novel memory surface known as Deep Learning (DL) memory surface. DL memory surface encodes the temporal information readily available from these sensors while retaining the sparsity of event data. Since there is no existing dataset for anomaly detection in the event domain, we also provide an anomaly detection event dataset with a set of anomalies. We empirically validate our anomaly detection architecture, composed of sparse convolutional layers, on this proposed and online dataset. Careful analysis of the anomaly detection network reveals that the presented method results in a massive reduction in computational complexity with good performance compared to previous state-of-the-art conventional frame-based anomaly detection networks.

Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks

Learning synaptic weights of spiking neural network (SNN) models that can reproduce target spike trains from provided neural firing data is a central problem in computational neuroscience and spike-based computing. The discovery of the optimal weight values can be posed as a supervised learning task wherein the weights of the model network are chosen to maximize the similarity between the target spike trains and the model outputs. It is still largely unknown whether optimizing spike train similarity of highly recurrent SNNs produces weight matrices similar to those of the ground truth model. To this end, we propose flexible heuristic supervised learning rules, termed Pre-Synaptic Pool Modification (PSPM), that rely on stochastic weight updates in order to produce spikes within a short window of the desired times and eliminate spikes outside of this window. PSPM improves spike train similarity for all-to-all SNNs and makes no assumption about the post-synaptic potential of the neurons or the structure of the network since no gradients are required. We test whether optimizing for spike train similarity entails the discovery of accurate weights and explore the relative contributions of local and homeostatic weight updates. Although PSPM improves similarity between spike trains, the learned weights often differ from the weights of the ground truth model, implying that connectome inference from spike data may require additional constraints on connectivity statistics. We also find that spike train similarity is sensitive to local updates, but other measures of network activity such as avalanche distributions, can be learned through synaptic homeostasis.

Data and Power Efficient Intelligence with Neuromorphic Learning Machines

The success of deep networks and recent industry involvement in brain-inspired computing is igniting a widespread interest in neuromorphic hardware that emulates the biological processes of the brain on an electronic substrate. This review explores interdisciplinary approaches anchored in machine learning theory that enable the applicability of neuromorphic technologies to real-world, human-centric tasks. We find that (1) recent work in binary deep networks and approximate gradient descent learning are strikingly compatible with a neuromorphic substrate; (2) where real-time adaptability and autonomy are necessary, neuromorphic technologies can achieve significant advantages over main-stream ones; and (3) challenges in memory technologies, compounded by a tradition of bottom-up approaches in the field, block the road to major breakthroughs. We suggest that a neuromorphic learning framework, tuned specifically for the spatial and temporal constraints of the neuromorphic substrate, will help guiding hardware algorithm co-design and deploying neuromorphic hardware for proactive learning of real-world data.

Responses of Leaky Integrate-and-Fire Neurons to a Plurality of Stimuli in Their Receptive Fields

A fundamental question concerning the way the visual world is represented in our brain is how a cortical cell responds when its classical receptive field contains a plurality of stimuli. Two opposing models have been proposed. In the response-averaging model, the neuron responds with a weighted average of all individual stimuli. By contrast, in the probability-mixing model, the cell responds to a plurality of stimuli as if only one of the stimuli were present. Here we apply the probability-mixing and the response-averaging model to leaky integrate-and-fire neurons, to describe neuronal behavior based on observed spike trains. We first estimate the parameters of either model using numerical methods, and then test which model is most likely to have generated the observed data. Results show that the parameters can be successfully estimated and the two models are distinguishable using model selection.

Design of Spiking Central Pattern Generators for Multiple Locomotion Gaits in Hexapod Robots by Christiansen Grammar Evolution

This paper presents a method to design Spiking Central Pattern Generators (SCPGs) to achieve locomotion at different frequencies on legged robots. It is validated through embedding its designs into a Field-Programmable Gate Array (FPGA) and implemented on a real hexapod robot. The SCPGs are automatically designed by means of a Christiansen Grammar Evolution (CGE)-based methodology. The CGE performs a solution for the configuration (synaptic weights and connections) for each neuron in the SCPG. This is carried out through the indirect representation of candidate solutions that evolve to replicate a specific spike train according to a locomotion pattern (gait) by measuring the similarity between the spike trains and the SPIKE distance to lead the search to a correct configuration. By using this evolutionary approach, several SCPG design specifications can be explicitly added into the SPIKE distance-based fitness function, such as looking for Spiking Neural Networks (SNNs) with minimal connectivity or a Central Pattern Generator (CPG) able to generate different locomotion gaits only by changing the initial input stimuli. The SCPG designs have been successfully implemented on a Spartan 6 FPGA board and a real time validation on a 12 Degrees Of Freedom (DOFs) hexapod robot is presented.

PyNCS: a microkernel for high-level definition and configuration of neuromorphic electronic systems

Neuromorphic hardware offers an electronic substrate for the realization of asynchronous event-based sensory-motor systems and large-scale spiking neural network architectures. In order to characterize these systems, configure them, and carry out modeling experiments, it is often necessary to interface them to workstations. The software used for this purpose typically consists of a large monolithic block of code which is highly specific to the hardware setup used. While this approach can lead to highly integrated hardware/software systems, it hampers the development of modular and reconfigurable infrastructures thus preventing a rapid evolution of such systems. To alleviate this problem, we propose PyNCS, an open-source front-end for the definition of neural network models that is interfaced to the hardware through a set of Python Application Programming Interfaces (APIs). The design of PyNCS promotes modularity, portability and expandability and separates implementation from hardware description. The high-level front-end that comes with PyNCS includes tools to define neural network models as well as to create, monitor and analyze spiking data. Here we report the design philosophy behind the PyNCS framework and describe its implementation. We demonstrate its functionality with two representative case studies, one using an event-based neuromorphic vision sensor, and one using a set of multi-neuron devices for carrying out a cognitive decision-making task involving state-dependent computation. PyNCS, already applicable to a wide range of existing spike-based neuromorphic setups, will accelerate the development of hybrid software/hardware neuromorphic systems, thanks to its code flexibility. The code is open-source and available online at https://github.com/inincs/pyNCS.

Synthesis of neural networks for spatio-temporal spike pattern recognition and processing

The advent of large scale neural computational platforms has highlighted the lack of algorithms for synthesis of neural structures to perform predefined cognitive tasks. The Neural Engineering Framework (NEF) offers one such synthesis, but it is most effective for a spike rate representation of neural information, and it requires a large number of neurons to implement simple functions. We describe a neural network synthesis method that generates synaptic connectivity for neurons which process time-encoded neural signals, and which makes very sparse use of neurons. The method allows the user to specify—arbitrarily—neuronal characteristics such as axonal and dendritic delays, and synaptic transfer functions, and then solves for the optimal input-output relationship using computed dendritic weights. The method may be used for batch or online learning and has an extremely fast optimization process. We demonstrate its use in generating a network to recognize speech which is sparsely encoded as spike times.

A simple model of mechanotransduction in primate glabrous skin

Tactile stimulation of the hand evokes highly precise and repeatable patterns of activity in mechanoreceptive afferents; the strength (i.e., firing rate) and timing of these responses have been shown to convey stimulus information. To achieve an understanding of the mechanisms underlying the representation of tactile stimuli in the nerve, we developed a two-stage computational model consisting of a nonlinear mechanical transduction stage followed by a generalized integrate-and-fire mechanism. The model improves upon a recently published counterpart in two important ways. First, complexity is dramatically reduced (at least one order of magnitude fewer parameters). Second, the model comprises a saturating nonlinearity and therefore can be applied to a much wider range of stimuli. We show that both the rate and timing of afferent responses are predicted with remarkable precision and that observed adaptation patterns and threshold behavior are well captured. We conclude that the responses of mechanoreceptive afferents can be understood using a very parsimonious mechanistic model, which can then be used to accurately simulate the responses of afferent populations.

Parameter estimation of a spiking silicon neuron

Spiking neuron models are used in a multitude of tasks ranging from understanding neural behavior at its most basic level to neuroprosthetics. Parameter estimation of a single neuron model, such that the model's output matches that of a biological neuron is an extremely important task. Hand tuning of parameters to obtain such behaviors is a difficult and time consuming process. This is further complicated when the neuron is instantiated in silicon (an attractive medium in which to implement these models) as fabrication imperfections make the task of parameter configuration more complex. In this paper we show two methods to automate the configuration of a silicon (hardware) neuron's parameters. First, we show how a Maximum Likelihood method can be applied to a leaky integrate and fire silicon neuron with spike induced currents to fit the neuron's output to desired spike times. We then show how a distance based method which approximates the negative log likelihood of the lognormal distribution can also be used to tune the neuron's parameters. We conclude that the distance based method is better suited for parameter configuration of silicon neurons due to its superior optimization speed.

Tunable neuromimetic integrated system for emulating cortical neuron models

Nowadays, many software solutions are currently available for simulating neuron models. Less conventional than software-based systems, hardware-based solutions generally combine digital and analog forms of computation. In previous work, we designed several neuromimetic chips, including the Galway chip that we used for this paper. These silicon neurons are based on the Hodgkin–Huxley formalism and they are optimized for reproducing a large variety of neuron behaviors thanks to tunable parameters. Due to process variation and device mismatch in analog chips, we use a full-custom fitting method in voltage-clamp mode to tune our neuromimetic integrated circuits. By comparing them with experimental electrophysiological data of these cells, we show that the circuits can reproduce the main firing features of cortical cell types. In this paper, we present the experimental measurements of our system which mimic the four most prominent biological cells: fast spiking, regular spiking, intrinsically bursting, and low-threshold spiking neurons into analog neuromimetic integrated circuit dedicated to cortical neuron simulations. This hardware and software platform will allow to improve the hybrid technique, also called “dynamic-clamp,” that consists of connecting artificial and biological neurons to study the function of neuronal circuits.

Biophysical Neural Spiking, Bursting, and Excitability Dynamics in Reconfigurable Analog VLSI

We study a range of neural dynamics under variations in biophysical parameters underlying extended Morris-Lecar and Hodgkin-Huxley models in three gating variables. The extended models are implemented in NeuroDyn, a four neuron, twelve synapse continuous-time analog VLSI programmable neural emulation platform with generalized channel kinetics and biophysical membrane dynamics. The dynamics exhibit a wide range of time scales extending beyond 100 ms neglected in typical silicon models of tonic spiking neurons. Circuit simulations and measurements show transition from tonic spiking to tonic bursting dynamics through variation of a single conductance parameter governing calcium recovery. We similarly demonstrate transition from graded to all-or-none neural excitability in the onset of spiking dynamics through the variation of channel kinetic parameters governing the speed of potassium activation. Other combinations of variations in conductance and channel kinetic parameters give rise to phasic spiking and spike frequency adaptation dynamics. The NeuroDyn chip consumes 1.29 mW and occupies 3 mm × 3 mm in 0.5 μm CMOS, supporting emerging developments in neuromorphic silicon-neuron interfaces.

Estimating parameters of generalized integrate-and-fire neurons from the maximum likelihood of spike trains

When a neuronal spike train is observed, what can we deduce from it about the properties of the neuron that generated it? A natural way to answer this question is to make an assumption about the type of neuron, select an appropriate model for this type, and then choose the model parameters as those that are most likely to generate the observed spike train. This is the maximum likelihood method. If the neuron obeys simple integrate-and-fire dynamics, Paninski, Pillow, and Simoncelli (2004) showed that its negative log-likelihood function is convex and that, at least in principle, its unique global minimum can thus be found by gradient descent techniques. Many biological neurons are, however, known to generate a richer repertoire of spiking behaviors than can be explained in a simple integrate-and-fire model. For instance, such a model retains only an implicit (through spike-induced currents), not an explicit, memory of its input; an example of a physiological situation that cannot be explained is the absence of firing if the input current is increased very slowly. Therefore, we use an expanded model (Mihalas & Niebur, 2009 ), which is capable of generating a large number of complex firing patterns while still being linear. Linearity is important because it maintains the distribution of the random variables and still allows maximum likelihood methods to be used. In this study, we show that although convexity of the negative log-likelihood function is not guaranteed for this model, the minimum of this function yields a good estimate for the model parameters, in particular if the noise level is treated as a free parameter. Furthermore, we show that a nonlinear function minimization method (r-algorithm with space dilation) usually reaches the global minimum.

Implementation study of an analog spiking neural network for assisting cardiac delay prediction in a cardiac resynchronization therapy device

In this paper, we aim at developing an analog spiking neural network (SNN) for reinforcing the performance of conventional cardiac resynchronization therapy (CRT) devices (also called biventricular pacemakers). Targeting an alternative analog solution in 0.13- μm CMOS technology, this paper proposes an approach to improve cardiac delay predictions in every cardiac period in order to assist the CRT device to provide real-time optimal heartbeats. The primary analog SNN architecture is proposed and its implementation is studied to fulfill the requirement of very low energy consumption. By using the Hebbian learning and reinforcement learning algorithms, the intended adaptive CRT device works with different functional modes. The simulations of both learning algorithms have been carried out, and they were shown to demonstrate the global functionalities. To improve the realism of the system, we introduce various heart behavior models (with constant/variable heart rates) that allow pathologic simulations with/without noise on the signals of the input sensors. The simulations of the global system (pacemaker models coupled with heart models) have been investigated and used to validate the analog spiking neural network implementation.