Share This Author
BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python
It is argued that this package facilitates the use of spiking networks for large-scale machine learning problems and some simple examples by using BindsNET in practice are shown.
Locally Connected Spiking Neural Networks for Unsupervised Feature Learning
Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks
This work is the first to achieve state-of-the-art performance on multiple Atari games with SNNs and serves as a benchmark for the conversion of DQNs to SNNS and paves the way for further research on solving reinforcement learning tasks with Snns.
Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to Atari Breakout game
Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI games
- Devdhar Patel, Hananel Hazan, D. J. Saunders, H. Siegelmann, R. Kozma
- Computer ScienceArXiv
- 26 March 2019
This paper provides a proof of principle of the conversion of standard NN to SNN, and shows that the SNN has improved robustness to occlusion in the input image, paving the way for future research to robust Deep RL applications.
Unsupervised Features Extracted using Winner-Take-All Mechanism Lead to Robust Image Classification
- Devdhar Patel, R. Kozma
- Computer ScienceInternational Joint Conference on Neural Networks…
- 1 July 2020
It is demonstrated that features extracted in an unsupervised manner using the biologically inspired Hebbian learning rule in a winner-take-all setting, perform competitively with BP on the image classification task.
Optimization methods for improved efficiency and performance of Deep Q-Networks upon conversion to neuromorphic population platforms