no code implementations • 20 Feb 2022 • S. Fatemeh Seyyedsalehi, Mahdieh Soleymani, Hamid R. Rabiee
Because of the complex relationship between the computational path of output variables in structured models, a feature can affect the value of output through other ones.
1 code implementation • NeurIPS 2021 • Mohammadamin Banayeeanzade, Rasoul Mirzaiezadeh, Hosein Hasani, Mahdieh Soleymani
Deep neural networks have achieved human-level capabilities in various learning tasks.
no code implementations • NeurIPS 2020 • Hassan Hafez-Kolahi, Zeinab Golgooni, Shohreh Kasaei, Mahdieh Soleymani
This approach provides an insight into learning algorithms by considering the mutual information between the model and the training set.
no code implementations • NeurIPS 2019 • Hosein Hasani, Mahdieh Soleymani, Hamid Aghajan
Numerous neurophysiological studies have revealed that a large number of the primary visual cortex neurons operate in a regime called surround modulation.
no code implementations • 25 Sep 2019 • Amir Ali Moinfar, Amirkeivan Mohtashami, Mahdieh Soleymani, Ali Sharifi-Zarchi
Designing the architecture of deep neural networks (DNNs) requires human expertise and is a cumbersome task.
no code implementations • CVPR 2016 • Sarah Rastegar, Mahdieh Soleymani, Hamid R. Rabiee, Seyed Mohsen Shojaee
In this paper, we propose a multimodal deep learning framework (MDL-CW) that exploits the cross weights between representation of modalities, and try to gradually learn interactions of the modalities in a deep network manner (from low to high level interactions).