evt_MNIST: A spike based version of traditional MNIST

2016/04/22 by Mazdak Fatahi, Fatahi, Mazdak, Mahmood Ahmadi +7 · 1 citation
Computer Science · Engineering · Neuroscience · #Advanced Memory and Neural Computing #FOS: Computer and information sciences #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function #cs.NE

paper · pdf · doi:10.48550/arxiv.1604.06751

arxiv created 2016/04/22 · openalex publication_date 2016/04/22 · arxiv updated 2016/04/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Benchmarks and datasets have important role in evaluation of machine learning algorithms and neural network implementations. Traditional dataset for images such as MNIST is applied to evaluate efficiency of different training algorithms in neural networks. This demand is different in Spiking Neural Networks (SNN) as they require spiking inputs. It is widely believed, in the biological cortex the timing of spikes is irregular. Poisson distributions provide adequate descriptions of the irregularity in generating appropriate spikes. Here, we introduce a spike-based version of MNSIT (handwritten digits dataset),using Poisson distribution and show the Poissonian property of the generated streams. We introduce a new version of evt_MNIST which can be used for neural network evaluation.

Citations

• A Fast Learning Algorithm for Deep Belief Nets

Cited by

• Rethinking Time Encoding via Learnable Transformation Functions

Related

• Deep Spiking Neural Network with Spike Count based Learning Rule
• Reliable counting of weakly labeled concepts by a single spiking neuron model
• To Spike or Not to Spike, that is the Question
• Desire Backpropagation: A Lightweight Training Algorithm for Multi-Layer Spiking Neural Networks based on Spike-Timing-Dependent Plasticity
• Ensembles of Spiking Neural Networks