File Classification Based on Spiking Neural Networks

  title={File Classification Based on Spiking Neural Networks},
  author={Ana Stanojevi{\'c} and Giovanni Cherubini and Timoleon Moraitis and Abu Sebastian},
  journal={2020 IEEE International Symposium on Circuits and Systems (ISCAS)},
In this paper, we propose a system for file classification in large data sets based on spiking neural networks (SNNs). File information contained in key-value metadata pairs is mapped by a novel correlative temporal encoding scheme to spike patterns that are input to an SNN. The correlation between input spike patterns is determined by a file similarity measure. Unsupervised training of such networks using spike-timing-dependent plasticity (STDP) is addressed first. Then, supervised SNN… 

Figures and Tables from this paper

End-to-End Learning of Neuromorphic Wireless Systems for Low-Power Edge Artificial Intelligence

An end-to-end training procedure is introduced that treats the cascade of encoder, channel, and decoder as a probabilistic SNN-based autoencoder that implements Joint Source-Channel Coding (JSCC).

Spiking Neural Networks—Part III: Neuromorphic Communications

This letter explores two ways in which Spiking Neural Networks (SNNs) can help address open problems in machine learning on battery-powered devices that are connected via bandwidth-constrained channels, and discusses federated learning for the distributed training of SNNs.



Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding

This work examines the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code and finds the FILT rule to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision.

Encoding Spike Patterns in Multilayer Spiking Neural Networks

This work introduces a learning rule for spiking networks containing hidden neurons which optimizes the likelihood of generating desired output spiking patterns and shows the proposed learning rule allows for a large number of accurate input-output spike pattern mappings to be learnt.

A comparative study on spiking neural network encoding schema: implemented with cloud computing

This is the first comprehensive study to discuss encoding algorithms in SNNs in details, which involved the advantages, disadvantages and when and where the authors can use and where the encoding algorithms are implemented, with focusing on some examples implement SNN in cloud computing generally.

Unsupervised learning of digit recognition using spike-timing-dependent plasticity

A SNN for digit recognition which is based on mechanisms with increased biological plausibility, i.e., conductance-based instead of current-based synapses, spike-timing-dependent plasticity with time-dependent weight change, lateral inhibition, and an adaptive spiking threshold is presented.

Introduction to spiking neural networks: Information processing, learning and applications.

This paper summarizes basic properties of spiking neurons and spiking networks, and focuses, specifically, on models of spike-based information coding, synaptic plasticity and learning.

Deep Learning in Spiking Neural Networks

Third Generation Neural Networks: Spiking Neural Networks

An overview of the development of spiking neurons and SNNs within the context of feedforward networks is presented, and insight into their potential for becoming the next generation neural networks is provided.

Deep Learning With Spiking Neurons: Opportunities and Challenges

This review addresses the opportunities that deep spiking networks offer and investigates in detail the challenges associated with training SNNs in a way that makes them competitive with conventional deep learning, but simultaneously allows for efficient mapping to hardware.

Error-backpropagation in temporally encoded networks of spiking neurons

Efficient Computation in Adaptive Artificial Spiking Neural Networks

Adaptive spike-time coding based on the firing rate limiting adaptation phenomenon observed in biological spiking neurons is used, and the resulting Adaptive SNNs (AdSNNs) can carry out inference in deep neural networks using up to an order of magnitude fewer spikes compared to previous SNNS.