Extended liquid state machines for speech recognition

Co-learning synaptic delays, weights and adaptation in spiking neural networks

Spiking neural network (SNN) distinguish themselves from artificial neural network (ANN) because of their inherent temporal processing and spike-based computations, enabling a power-efficient implementation in neuromorphic hardware. In this study, we demonstrate that data processing with spiking neurons can be enhanced by co-learning the synaptic weights with two other biologically inspired neuronal features: (1) a set of parameters describing neuronal adaptation processes and (2) synaptic propagation delays. The former allows a spiking neuron to learn how to specifically react to incoming spikes based on its past. The trained adaptation parameters result in neuronal heterogeneity, which leads to a greater variety in available spike patterns and is also found in the brain. The latter enables to learn to explicitly correlate spike trains that are temporally distanced. Synaptic delays reflect the time an action potential requires to travel from one neuron to another. We show that each of the co-learned features separately leads to an improvement over the baseline SNN and that the combination of both leads to state-of-the-art SNN results on all speech recognition datasets investigated with a simple 2-hidden layer feed-forward network. Our SNN outperforms the benchmark ANN on the neuromorphic datasets (Spiking Heidelberg Digits and Spiking Speech Commands), even with fewer trainable parameters. On the 35-class Google Speech Commands dataset, our SNN also outperforms a GRU of similar size. Our study presents brain-inspired improvements in SNN that enable them to excel over an equivalent ANN of similar size on tasks with rich temporal dynamics.

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.

Neural simulation pipeline: Enabling container-based simulations on-premise and in public clouds

In this study, we explore the simulation setup in computational neuroscience. We use GENESIS, a general purpose simulation engine for sub-cellular components and biochemical reactions, realistic neuron models, large neural networks, and system-level models. GENESIS supports developing and running computer simulations but leaves a gap for setting up today's larger and more complex models. The field of realistic models of brain networks has overgrown the simplicity of earliest models. The challenges include managing the complexity of software dependencies and various models, setting up model parameter values, storing the input parameters alongside the results, and providing execution statistics. Moreover, in the high performance computing (HPC) context, public cloud resources are becoming an alternative to the expensive on-premises clusters. We present Neural Simulation Pipeline (NSP), which facilitates the large-scale computer simulations and their deployment to multiple computing infrastructures using the infrastructure as the code (IaC) containerization approach. The authors demonstrate the effectiveness of NSP in a pattern recognition task programmed with GENESIS, through a custom-built visual system, called RetNet(8 × 5,1) that uses biologically plausible Hodgkin-Huxley spiking neurons. We evaluate the pipeline by performing 54 simulations executed on-premise, at the Hasso Plattner Institute's (HPI) Future Service-Oriented Computing (SOC) Lab, and through the Amazon Web Services (AWS), the biggest public cloud service provider in the world. We report on the non-containerized and containerized execution with Docker, as well as present the cost per simulation in AWS. The results show that our neural simulation pipeline can reduce entry barriers to neural simulations, making them more practical and cost-effective.