no code implementations • 30 Sep 2020 • Weihao Tan, Devdhar Patel, Robert Kozma
The present work focuses on using SNNs in combination with deep reinforcement learning in ATARI games, which involves additional complexity as compared to image classification.
no code implementations • 29 Aug 2020 • Stephen Chung, Robert Kozma
Spiking neuron networks have been used successfully to solve simple reinforcement learning tasks with continuous action set applying learning rules based on spike-timing-dependent plasticity (STDP).
1 code implementation • NeurIPS Workshop Neuro_AI 2019 • Sneha Aenugu, Abhishek Sharma, Sasikiran Yelamarthi, Hananel Hazan, Philip S. Thomas, Robert Kozma
Neuroscientific theory suggests that dopaminergic neurons broadcast global reward prediction errors to large areas of the brain influencing the synaptic plasticity of the neurons in those regions.
1 code implementation • 5 Sep 2019 • Daniel J. Saunders, Cooper Sigrist, Kenneth Chaney, Robert Kozma, Hava T. Siegelmann
To our knowledge, this is the first general-purpose implementation of mini-batch processing in a spiking neural networks simulator, which works with arbitrary neuron and synapse models.
no code implementations • 4 Jun 2019 • Hananel Hazan, Daniel J. Saunders, Darpan T. Sanghavi, Hava Siegelmann, Robert Kozma
Spiking neural networks (SNNs) with a lattice architecture are introduced in this work, combining several desirable properties of SNNs and self-organized maps (SOMs).
no code implementations • 12 Apr 2019 • Daniel J. Saunders, Devdhar Patel, Hananel Hazan, Hava T. Siegelmann, Robert Kozma
In recent years, Spiking Neural Networks (SNNs) have demonstrated great successes in completing various Machine Learning tasks.
3 code implementations • 26 Mar 2019 • Devdhar Patel, Hananel Hazan, Daniel J. Saunders, Hava Siegelmann, Robert Kozma
Previous studies in image classification domain demonstrated that standard NNs (with ReLU nonlinearity) trained using supervised learning can be converted to SNNs with negligible deterioration in performance.
no code implementations • 24 Aug 2018 • Daniel J. Saunders, Hava T. Siegelmann, Robert Kozma, Miklós Ruszinkó
Spiking neural networks are motivated from principles of neural systems and may possess unexplored advantages in the context of machine learning.
no code implementations • 24 Jul 2018 • Hananel Hazan, Daniel J. Saunders, Darpan T. Sanghavi, Hava T. Siegelmann, Robert Kozma
We present a system comprising a hybridization of self-organized map (SOM) properties with spiking neural networks (SNNs) that retain many of the features of SOMs.
1 code implementation • 4 Jun 2018 • Hananel Hazan, Daniel J. Saunders, Hassaan Khan, Darpan T. Sanghavi, Hava T. Siegelmann, Robert Kozma
In this paper, we describe a new Python package for the simulation of spiking neural networks, specifically geared towards machine learning and reinforcement learning.
no code implementations • 15 Aug 2013 • Yury Sokolov, Robert Kozma, Ludmilla D. Werbos, Paul J. Werbos
This paper provides new stability results for Action-Dependent Heuristic Dynamic Programming (ADHDP), using a control algorithm that iteratively improves an internal model of the external world in the autonomous system based on its continuous interaction with the environment.