Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Patel, Devdhar"'
Autor:
Patel, Devdhar, Siegelmann, Hava
Reinforcement learning (RL) is rapidly reaching and surpassing human-level control capabilities. However, state-of-the-art RL algorithms often require timesteps and reaction times significantly faster than human capabilities, which is impractical in
Externí odkaz:
http://arxiv.org/abs/2410.08979
Publikováno v:
Neural Computation, 1-30 (2024)
The current reinforcement learning framework focuses exclusively on performance, often at the expense of efficiency. In contrast, biological control achieves remarkable performance while also optimizing computational energy expenditure and decision f
Externí odkaz:
http://arxiv.org/abs/2305.18701
Autor:
Patel, Devdhar, Russell, Joshua, Walsh, Francesca, Rahman, Tauhidur, Sejnowski, Terrence, Siegelmann, Hava
We present temporally layered architecture (TLA), a biologically inspired system for temporally adaptive distributed control. TLA layers a fast and a slow controller together to achieve temporal abstraction that allows each layer to focus on a differ
Externí odkaz:
http://arxiv.org/abs/2301.00723
Autor:
Patel, Devdhar, Siegelmann, Hava
Deep neural networks have long training and processing times. Early exits added to neural networks allow the network to make early predictions using intermediate activations in the network in time-sensitive applications. However, early exits increase
Externí odkaz:
http://arxiv.org/abs/2212.12866
Autor:
Patel, Devdhar, Siegelmann, Hava T.
Publikováno v:
In Biochemical and Biophysical Research Communications 31 December 2024 741
Spiking neural networks (SNNs) have great potential for energy-efficient implementation of Deep Neural Networks (DNNs) on dedicated neuromorphic hardware. Recent studies demonstrated competitive performance of SNNs compared with DNNs on image classif
Externí odkaz:
http://arxiv.org/abs/2009.14456
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
In recent years, Spiking Neural Networks (SNNs) have demonstrated great successes in completing various Machine Learning tasks. We introduce a method for learning image features by \textit{locally connected layers} in SNNs using spike-timing-dependen
Externí odkaz:
http://arxiv.org/abs/1904.06269
Deep Reinforcement Learning (RL) demonstrates excellent performance on tasks that can be solved by trained policy. It plays a dominant role among cutting-edge machine learning approaches using multi-layer Neural networks (NNs). At the same time, Deep
Externí odkaz:
http://arxiv.org/abs/1903.11012
Publikováno v:
In Knowledge-Based Systems 6 April 2022 241