Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain

Abstract

The advantage of spiking neural networks (SNNs) over their predecessors is their ability to spike, enabling them to use spike timing for coding and efficient computing. A neuromorphic dataset should allow a neuromorphic algorithm to clearly show that a SNN is able to perform better on the dataset than an ANN. We have analyzed both N-MNIST and N-Caltech101 along these lines, but focus our study on N-MNIST. First we evaluate if additional information is encoded in the time domain in a neuromoprhic dataset. We show that an ANN trained with backpropagation on frame based versions of N-MNIST and N-Caltech101 images achieve 99.23% and 78.01% accuracy. These are the best classification accuracies obtained on these datasets to date. Second we present the first unsupervised SNN to be trained on N-MNIST and demonstrate results of 91.78%. We also use this SNN for further experiments on N-MNIST to show that rate based SNNs perform better, and precise spike timings are not important in N-MNIST. N-MNIST does not, therefore, highlight the unique ability of SNNs. The conclusion of this study opens an important question in neuromorphic engineering - what, then, constitutes a good neuromorphic dataset?

References in corpus (10)

• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• STDP-based spiking deep convolutional neural networks for object recognition
• 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
• HFirst: A Temporal Approach to Object Recognition
• Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)
• Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
• Event-based Gesture Recognition with Dynamic Background Suppression using Smartphone Computational Capabilities
• Classifying neuromorphic data using a deep learning framework for image classification

Cited by in corpus (9)

• Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)
• An optimised deep spiking neural network architecture without gradients
• A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks
• Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
• Deep Spiking Neural Network with Spike Count based Learning Rule
• Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform
• An efficient and perceptually motivated auditory neural encoding and decoding algorithm for spiking neural networks
• Building time-surfaces by exploiting the complex volatility of an ECRAM memristor
• Neuromorphic Algorithm-hardware Codesign for Temporal Pattern Learning