Search Results for author: Saeed Reza Kheradpisheh

Found 18 papers, 8 papers with code

Meta-Learning in Spiking Neural Networks with Reward-Modulated STDP

no code implementations7 Jun 2023 Arsham Gholamzadeh Khoee, Alireza Javaheri, Saeed Reza Kheradpisheh, Mohammad Ganjtabesh

The human brain constantly learns and rapidly adapts to new situations by integrating acquired knowledge and experiences into memory.

Hippocampus Meta-Learning

Spiking neural networks trained via proxy

1 code implementation27 Sep 2021 Saeed Reza Kheradpisheh, Maryam Mirsadeghi, Timothée Masquelier

By assuming IF neuron with rate-coding as an approximation of ReLU, we backpropagate the error of the SNN in the proxy ANN to update the shared weights, simply by replacing the ANN final output with that of the SNN.

BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks

1 code implementation12 Sep 2021 Hafez Ghaemi, Erfan Mirzaei, Mahbod Nouri, Saeed Reza Kheradpisheh

Brain-inspired computation and information processing alongside compatibility with neuromorphic hardware have made spiking neural networks (SNN) a promising method for solving learning tasks in machine learning (ML).

Image Classification

Spike time displacement based error backpropagation in convolutional spiking neural networks

no code implementations31 Aug 2021 Maryam Mirsadeghi, Majid Shalchian, Saeed Reza Kheradpisheh, Timothée Masquelier

To do so, we consider a convolutional SNN (CSNN) with two sets of weights: real-valued weights that are updated in the backward pass and their signs, binary weights, that are employed in the feedforward process.

Image Classification

BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning

1 code implementation8 Jul 2020 Saeed Reza Kheradpisheh, Maryam Mirsadeghi, Timothée Masquelier

We recently proposed the S4NN algorithm, essentially an adaptation of backpropagation to multilayer spiking neural networks that use simple non-leaky integrate-and-fire neurons and a form of temporal coding known as time-to-first-spike coding.

Action Recognition Using Supervised Spiking Neural Networks

no code implementations9 Nov 2019 Aref Moqadam Mehr, Saeed Reza Kheradpisheh, Hadi Farahani

Biological neurons use spikes to process and learn temporally dynamic inputs in an energy and computationally efficient way.

Action Recognition Image Categorization

S4NN: temporal backpropagation for spiking neural networks with one spike per neuron

1 code implementation21 Oct 2019 Saeed Reza Kheradpisheh, Timothée Masquelier

In particular, in the readout layer, the first neuron to fire determines the class of the stimulus.

Deep Learning in Spiking Neural Networks

2 code implementations22 Apr 2018 Amirhossein Tavanaei, Masoud Ghodrati, Saeed Reza Kheradpisheh, Timothee Masquelier, Anthony S. Maida

In this approach, a deep (multilayer) artificial neural network (ANN) is trained in a supervised manner using backpropagation.

Optimal localist and distributed coding of spatiotemporal spike patterns through STDP and coincidence detection

no code implementations1 Mar 2018 Timothée Masquelier, Saeed Reza Kheradpisheh

Here we investigated how a single spiking neuron can optimally respond to one given pattern (localist coding), or to either one of several patterns (distributed coding, i. e. the neuron's response is ambiguous but the identity of the pattern could be inferred from the response of multiple neurons), but not to random inputs.

First-spike based visual categorization using reward-modulated STDP

no code implementations25 May 2017 Milad Mozafari, Saeed Reza Kheradpisheh, Timothée Masquelier, Abbas Nowzari-Dalini, Mohammad Ganjtabesh

In the highest layers, each neuron was assigned to an object category, and it was assumed that the stimulus category was the category of the first neuron to fire.

Game of Go Object Recognition +1

STDP-based spiking deep convolutional neural networks for object recognition

1 code implementation4 Nov 2016 Saeed Reza Kheradpisheh, Mohammad Ganjtabesh, Simon J. Thorpe, Timothée Masquelier

Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron.

Object Recognition

Humans and deep networks largely agree on which kinds of variation make object recognition harder

no code implementations21 Apr 2016 Saeed Reza Kheradpisheh, Masoud Ghodrati, Mohammad Ganjtabesh, Timothée Masquelier

This feed-forward architecture has inspired a new generation of bio-inspired computer vision systems called deep convolutional neural networks (DCNN), which are currently the best algorithms for object recognition in natural images.

Object Object Recognition +1

Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition

no code implementations17 Aug 2015 Saeed Reza Kheradpisheh, Masoud Ghodrati, Mohammad Ganjtabesh, Timothée Masquelier

Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases.

Object Recognition

Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition

no code implementations15 Apr 2015 Saeed Reza Kheradpisheh, Mohammad Ganjtabesh, Timothée Masquelier

Retinal image of surrounding objects varies tremendously due to the changes in position, size, pose, illumination condition, background context, occlusion, noise, and nonrigid deformations.

Object Object Categorization +1

Cannot find the paper you are looking for? You can Submit a new open access paper.