Sotabase

Career

· Co-Founder And CTO, Vayu Robotics2022–
· Staff Research Scientist - Machine Learning, Apple2018–2022
· Staff ML Engineer, Apple2017–2018
· Co-Founder, Clarevision Research (Acquired by Apple)2015–2016
· Research Intern, Google2013–2013
· Research Intern, Google2012–2013
· Graduate Student, University of Toronto2011–2017
· Intern, Microsoft Research Silicon Valley2010–2010
· Intern, Ecole Centrale Paris2009–2009

Publications (42)

Dropout: a simple way to prevent neural networks from overfitting
Journal of machine learning research · 2014
42,312
cited
Improving neural networks by preventing co-adaptation of feature detectors
arXiv.org · 2012
7,937
cited
Unsupervised Learning of Video Representations using LSTMs
International Conference on Machine Learning · 2015
2,691
cited
Multimodal learning with deep Boltzmann machines
Journal of machine learning research · 2012
1,785
cited
Unsupervised Learning of Visual Representations using Videos
2015
998
cited
Improving Neural Networks with Dropout
2013
305
cited
Discriminative Transfer Learning with Tree-based Priors
Neural Information Processing Systems · 2013
222
cited
MatRaptor: A Sparse-Sparse Matrix Multiplication Accelerator Based on Row-Wise Product
Micro · 2020
220
cited
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
International Conference on Machine Learning · 2021
212
cited
Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
British Machine Vision Conference · 2015
206
cited
Learning Representations for Multimodal Data with Deep Belief Nets
2012
205
cited
Modeling Documents with Deep Boltzmann Machines
Conference on Uncertainty in Artificial Intelligence · 2013
187
cited
An Attention Free Transformer
arXiv.org · 2021
166
cited
Unconstrained Scene Generation with Locally Conditioned Radiance Fields
IEEE International Conference on Computer Vision · 2021
163
cited
Tensaurus: A Versatile Accelerator for Mixed Sparse-Dense Tensor Computations
International Symposium on High-Performance Computer Architecture · 2020
119
cited
Capsules with Inverted Dot-Product Attention Routing
International Conference on Learning Representations · 2020
91
cited
Learning Generative Models with Visual Attention
Neural Information Processing Systems · 2013
86
cited
Elective surgery system strengthening: development, measurement, and validation of the surgical preparedness index across 1632 hospitals in 119 countries
The Lancet · 2022
51
cited
T2S-Tensor: Productively Generating High-Performance Spatial Hardware for Dense Tensor Computations
IEEE Symposium on Field-Programmable Custom Computing Machines · 2019
51
cited
Enriching textbooks through data mining
ACM DEV '10 · 2010
49
cited
Sotabase