no code implementations • 1 Nov 2023 • Amir Hosein Fadaei, Mohammad-Reza A. Dehaqani
Traditionally, vision models have predominantly relied on spatial features extracted from static images, deviating from the continuous stream of spatiotemporal features processed by the brain in natural vision.
no code implementations • 31 Jan 2023 • Shahriar Rezghi Shirsavar, Mohammad-Reza A. Dehaqani
Several SNNs are implemented in this work with different learning rules (spike-timing-dependent plasticity and reinforcement learning) using Spyker that achieve significantly better runtimes, to prove the practicality of the library in the simulation of large-scale networks.
no code implementations • 8 Dec 2022 • Shahriar Rezghi Shirsavar, Abdol-Hossein Vahabie, Mohammad-Reza A. Dehaqani
Spiking neural networks (SNNs) have been around for a long time, and they have been investigated to understand the dynamics of the brain.
no code implementations • 31 Oct 2022 • Shahriar Rezghi Shirsavar, Mohammad-Reza A. Dehaqani
The proposed structure fractionalizes runtime and introduces an efficient approach to deep convolutional SNNs.
1 code implementation • Scientific Reports 2021 • Ramin Toosi, Mohammad Ali Akhaee, Mohammad-Reza A. Dehaqani
Here, we develop an automatic spike sorting algorithm based on adaptive spike detection and a mixture of skew-t distributions to address these distortions and instabilities.