Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain
Authors:
Open Access
- 25 March 2021
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 15
Abstract
A major characteristic of spiking neural networks (SNNs) over conventional artificial neural networks (ANNs) is their ability to spike, enabling them to use spike timing for coding and efficient computing. In this paper, we assess if neuromorphic datasets recorded from static images are able to evaluate the ability of SNNs to use spike timings in their calculations. We have analyzed N-MNIST, N-Caltech101 and DvsGesture along these lines, but focus our study on N-MNIST. First we evaluate if additional information is encoded in the time domain in a neuromorphic 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 comparable to the state of the art—showing that an algorithm that purely works on spatial data can classify these datasets. Second we compare N-MNIST and DvsGesture on two STDP algorithms, RD-STDP, that can classify only spatial data, and STDP-tempotron that classifies spatiotemporal data. We demonstrate that RD-STDP performs very well on N-MNIST, while STDP-tempotron performs better on DvsGesture. Since DvsGesture has a temporal dimension, it requires STDP-tempotron, while N-MNIST can be adequately classified by an algorithm that works on spatial data alone. This shows that precise spike timings are not important in N-MNIST. N-MNIST does not, therefore, highlight the ability of SNNs to classify temporal data. The conclusions of this paper open the question—what dataset can evaluate SNN ability to classify temporal data?Keywords
All Related Versions
This publication has 87 references indexed in Scilit:
- Multiplexing Stimulus Information through Rate and Temporal Codes in Primate Somatosensory CortexPLOS Biology, 2013
- Cortical dynamics during naturalistic sensory stimulations: Experiments and modelsJournal of Physiology-Paris, 2011
- A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision SensorIEEE Journal of Solid-State Circuits, 2008
- Bayesian Spiking Neurons I: InferenceNeural Computation, 2008
- Temporal precision in the neural code and the timescales of natural visionNature, 2007
- The Role of Temporal Structure in Human VisionBehavioral and Cognitive Neuroscience Reviews, 2005
- First spikes in ensembles of human tactile afferents code complex spatial fingertip eventsNature Neuroscience, 2004
- Statistical learning of higher-order temporal structure from visual shape sequences.Journal of Experimental Psychology: Learning, Memory, and Cognition, 2002
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997
- Stimulus-specific neuronal oscillations in orientation columns of cat visual cortex.Proceedings of the National Academy of Sciences, 1989