464 citations · 502 across the 13 of their papers we have counts for
10 papers · 1 filter
A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations
Sergio F. Chevtchenko, Yeshwanth Bethi, Teresa B. Ludermir +1
Reinforcement Learning (RL) provides a powerful framework for decision-making in complex environments. However, implementing RL in hardware-efficient and bio-inspired ways remains…
Efficient Implementation of a Multi-Layer Gradient-Free Online-Trainable Spiking Neural Network on FPGA
Ali Mehrabi, Yeshwanth Bethi, André van Schaik +2
This paper presents an efficient hardware implementation of the recently proposed Optimized Deep Event-driven Spiking Neural Network Architecture (ODESA). ODESA is the first networ…
An optimised deep spiking neural network architecture without gradients
Yeshwanth Bethi, Ying Xu, Gregory Cohen +2
We present an end-to-end trainable modular event-driven neural architecture that uses local synaptic and threshold adaptation rules to perform transformations between arbitrary spa…
Event-based Feature Extraction Using Adaptive Selection Thresholds
Saeed Afshar, Ying Xu, Jonathan Tapson +2
Unsupervised feature extraction algorithms form one of the most important building blocks in machine learning systems. These algorithms are often adapted to the event-based domain…
Investigation of event-based memory surfaces for high-speed tracking, unsupervised feature extraction and object recognition
Saeed Afshar, Gregory Cohen, Tara Julia Hamilton +2
In this paper we compare event-based decaying and time based-decaying memory surfaces for high-speed eventbased tracking, feature extraction, and object classification using an eve…
An Online Learning Algorithm for Neuromorphic Hardware Implementation
Chetan Singh Thakur, Runchun Wang, Saeed Afshar +4
We propose a sign-based online learning (SOL) algorithm for a neuromorphic hardware framework called Trainable Analogue Block (TAB). The TAB framework utilises the principles of ne…