activity
20072022
most citedBindsNET: A machine learning-oriented spiking neural networks library in Python

250 citations · 564 across the 20 of their papers we have counts for

collaborators

21 papers

math.MG2022

Optimal Horoball Packing Densities for Koszul-type tilings in Hyperbolic -space

Robert T. Kozma, Jenő Szirmai

We determine the optimal horoball packing densities for Koszul-type Coxeter simplex tilings in hyperbolic -space. Using a parametrization of horoballs by the Busemann function a…

math.PR2021★ 2 cited

Central Limit Theorem for Cocycles over Hyperbolic Systems

Alex Furman, Robert Thijs Kozma

We prove a Central Limit Theorem (CLT) in the non-commutative setting of random matrix products where the underlying process is driven by a subshift of finite type (SFT) with Marko…

cs.NE2020★ 6 cited

Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks

Weihao Tan, Devdhar Patel, Robert Kozma

Spiking neural networks (SNNs) have great potential for energy-efficient implementation of Deep Neural Networks (DNNs) on dedicated neuromorphic hardware. Recent studies demonstrat…

cs.LG2020★ 4 cited

Reinforcement Learning with Feedback-modulated TD-STDP

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…

cs.LG2019★ 3 cited

Reinforcement learning with a network of spiking agents

Sneha Aenugu, Abhishek Sharma, Sasikiran Yelamarthi +3

Neuroscientific theory suggests that dopaminergic neurons broadcast global reward prediction errors to large areas of the brain influencing the synaptic plasticity of the neurons i…

cs.NE2019★ 2 cited

Minibatch Processing in Spiking Neural Networks

Daniel J. Saunders, Cooper Sigrist, Kenneth Chaney +2

Spiking neural networks (SNNs) are a promising candidate for biologically-inspired and energy efficient computation. However, their simulation is notoriously time consuming, and ma…