M
Mohammad Ganjtabesh
Researcher at University of Tehran
Publications - 36
Citations - 1581
Mohammad Ganjtabesh is an academic researcher from University of Tehran. The author has contributed to research in topics: Spiking neural network & RNA. The author has an hindex of 14, co-authored 34 publications receiving 1186 citations. Previous affiliations of Mohammad Ganjtabesh include École Polytechnique.
Papers
More filters
Journal ArticleDOI
STDP-based spiking deep convolutional neural networks for object recognition
Saeed Reza Kheradpisheh,Saeed Reza Kheradpisheh,Mohammad Ganjtabesh,Simon J. Thorpe,Timothée Masquelier +4 more
TL;DR: The results suggest that the combination of STDP with latency coding may be a key to understanding the way that the primate visual system learns, its remarkable processing speed and its low energy consumption.
Journal ArticleDOI
Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
Saeed Reza Kheradpisheh,Saeed Reza Kheradpisheh,Masoud Ghodrati,Masoud Ghodrati,Mohammad Ganjtabesh,Timothée Masquelier +5 more
TL;DR: This work benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking to demonstrate that shallow nets can outperform deep nets and humans when variations are weak.
Journal ArticleDOI
First-Spike-Based Visual Categorization Using Reward-Modulated STDP
Milad Mozafari,Saeed Reza Kheradpisheh,Timothée Masquelier,Abbas Nowzari-Dalini,Mohammad Ganjtabesh +4 more
TL;DR: For the first time, it is shown that RL can be used efficiently to train a spiking neural network (SNN) to perform object recognition in natural images without using an external classifier.
Journal ArticleDOI
Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition
TL;DR: It is shown that the association of both biologically inspired network architecture and learning rule significantly improves the models' performance when facing challenging invariant object recognition problems.
Journal ArticleDOI
Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
Saeed Reza Kheradpisheh,Saeed Reza Kheradpisheh,Masoud Ghodrati,Masoud Ghodrati,Mohammad Ganjtabesh,Timothée Masquelier +5 more
TL;DR: In this paper, the authors compared eight state-of-the-art CNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking.