Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain
| Autor: | Yansong Chua, Haizhou Li, Laxmi R Iyer |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Computer science lcsh:RC321-571 spiking neural network Discriminative model Neural and Evolutionary Computing (cs.NE) neuromorphic benchmark lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry Original Research Spiking neural network spike timing dependent plasticity Artificial neural network business.industry General Neuroscience Computer Science - Neural and Evolutionary Computing Pattern recognition Backpropagation N-MNIST dataset Temporal database Neuromorphic engineering spike time coding Spike (software development) Artificial intelligence business MNIST database Neuroscience |
| Zdroj: | Frontiers in Neuroscience Frontiers in Neuroscience, Vol 15 (2021) |
| DOI: | 10.48550/arxiv.1807.01013 |
| Popis: | 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? |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|