The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks

Abstract

Spiking neural networks are the basis of versatile and power-efficient information processing in the brain. Although we currently lack a detailed understanding of how these networks compute, recently developed optimization techniques allow us to instantiate increasingly complex functional spiking neural networks in-silico. These methods hold the promise to build more efficient non-von-Neumann computing hardware and will offer new vistas in the quest of unraveling brain circuit function. To accelerate the development of such methods, objective ways to compare their performance are indispensable. Presently, however, there are no widely accepted means for comparing the computational performance of spiking neural networks. To address this issue, we introduce two spike-based classification datasets, broadly applicable to benchmark both software and neuromorphic hardware implementations of spiking neural networks. To accomplish this, we developed a general audio-to-spiking conversion procedure inspired by neurophysiology. Further, we applied this conversion to an existing and a novel speech dataset. The latter is the free, high-fidelity, and word-level aligned Heidelberg digit dataset that we created specifically for this study. By training a range of conventional and spiking classifiers, we show that leveraging spike timing information within these datasets is essential for good classification accuracy. These results serve as the first reference for future performance comparisons of spiking neural networks.

References in corpus (24)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Deep Learning in Spiking Neural Networks
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• STDP-based spiking deep convolutional neural networks for object recognition
• A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)
• SuperSpike: Supervised learning in multi-layer spiking neural networks
• SLAYER: Spike Layer Error Reassignment in Time
• Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures
• Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)
• Supervised Learning in Spiking Neural Networks with FORCE Training
• Neuromorphic Deep Learning Machines
• A sparse coding model with synaptically local plasticity and spiking neurons can account for the diverse shapes of V1 simple cell receptive fields
• Spiking Deep Networks with LIF Neurons
• Deep learning incorporating biologically-inspired neural dynamics
• Surrogate Gradient Learning in Spiking Neural Networks
• Learning universal computations with spikes
• Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
• An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
• Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
• Blackbox: A procedure for parallel optimization of expensive black-box functions
• Efficient Computation in Adaptive Artificial Spiking Neural Networks
• Closing the Accuracy Gap in an Event-Based Visual Recognition Task

Cited by in corpus (48)

• ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescales
• Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence
• STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks
• Spiker+: a framework for the generation of efficient Spiking Neural Networks FPGA accelerators for inference at the edge
• Fluctuation-driven initialization for spiking neural network training
• Advancing Spatio-Temporal Processing in Spiking Neural Networks through Adaptation
• Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs
• ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware
• Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
• Loss shaping enhances exact gradient learning with Eventprop in spiking neural networks
• Hardware/Software co-design with ADC-Less In-memory Computing Hardware for Spiking Neural Networks
• Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate
• Empirical study on the efficiency of Spiking Neural Networks with axonal delays, and algorithm-hardware benchmarking
• A Quantum Leaky Integrate-and-Fire Spiking Neuron and Network
• Special Session: Neuromorphic hardware design and reliability from traditional CMOS to emerging technologies
• SpikingJET: Enhancing Fault Injection for Fully and Convolutional Spiking Neural Networks
• Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks
• SpikePipe: Accelerated Training of Spiking Neural Networks via Inter-Layer Pipelining and Multiprocessor Scheduling
• Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
• SpikE: spike-based embeddings for multi-relational graph data
• Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks
• SpikeExplorer: hardware-oriented Design Space Exploration for Spiking Neural Networks on FPGA
• Adapting to time: Why nature may have evolved a diverse set of neurons
• Accelerating SNN Training with Stochastic Parallelizable Spiking Neurons
• FeNN: A RISC-V vector processor for Spiking Neural Network acceleration
• MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks
• Adaptive Approach For Sparse Representations Using The Locally Competitive Algorithm For Audio
• SNNGX: Securing Spiking Neural Networks with Genetic XOR Encryption on RRAM-based Neuromorphic Accelerator
• Understanding the Functional Roles of Modelling Components in Spiking Neural Networks
• Sparse Spiking Gradient Descent
• Spiketrum: An FPGA-based Implementation of a Neuromorphic Cochlea
• Hardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGA
• NeuroMorse: A Temporally Structured Dataset For Neuromorphic Computing
• Spiking mode-based neural networks
• Gated Parametric Neuron for Spike-based Audio Recognition
• Adaptive Central Frequencies Locally Competitive Algorithm for Speech
• Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation
• A flexible framework for structural plasticity in GPU-accelerated sparse spiking neural networks
• Three factor delay learning rules for spiking neural networks
• End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor
• Non-uniform Memory Partitioning For Low-Power Spiking Neural Networks
• A Linear Implementation of an Analog Resonate-and-Fire Neuron
• Convolutional Spiking-based GRU Cell for Spatio-temporal Data
• WaveSense: Efficient Temporal Convolutions with Spiking Neural Networks for Keyword Spotting
• State-Space Model Inspired Multiple-Input Multiple-Output Spiking Neurons
• Neuromorphic Algorithm-hardware Codesign for Temporal Pattern Learning
• Zero-Shot Temporal Resolution Domain Adaptation for Spiking Neural Networks
• Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems