Mohammad Pezeshki

Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks

Ying Zhang, Mohammad Pezeshki, Philémon Brakel et al. · 2016 · 336 citations

Natural Language Processing, Automatic Speech Recognition, Machine Learning +15

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

David Krueger, Tegan Maharaj, János Kramár et al. · PolyPublie (École Polytechnique de Montréal) · 2016 · 173 citations · Full text

Natural Language Processing, Zoneout Uses, Sequence Modelling +12

Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks

Ying Zhang, Mohammad Pezeshki, Philémon Brakel et al. · arXiv (Cornell University) · 2017 · 72 citations · Full text

Natural Language Processing, Engineering, Machine Learning +15

Deconstructing the Ladder Network Architecture

Mohammad Pezeshki, Linxi Fan, Philémon Brakel et al. · arXiv (Cornell University) · 2015 · 66 citations · Full text

Artificial Intelligence, Engineering, Machine Learning +19

Gradient Starvation: A Learning Proclivity in Neural Networks

Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio et al. · arXiv (Cornell University) · 2020 · 42 citations · Full text

Artificial Intelligence, Neural Scaling Law, Gradient Descent +13