J
Jonathan Cohen
Researcher at Nvidia
Publications - 51
Citations - 3870
Jonathan Cohen is an academic researcher from Nvidia. The author has contributed to research in topics: Solver & CUDA. The author has an hindex of 23, co-authored 50 publications receiving 3390 citations. Previous affiliations of Jonathan Cohen include Sony Broadcast & Professional Research Laboratories & Brown University.
Papers
More filters
Posted Content
cuDNN: Efficient Primitives for Deep Learning
Sharan Chetlur,Cliff Woolley,Philippe Vandermersch,Jonathan Cohen,John Tran,Bryan Catanzaro,Evan Shelhamer +6 more
TL;DR: A library similar in intent to BLAS, with optimized routines for deep learning workloads, that contains routines for GPUs, and similarly to the BLAS library, could be implemented for other platforms.
Proceedings ArticleDOI
Fast tridiagonal solvers on the GPU
TL;DR: To combine the benefits of the basic algorithms, this work proposes hybrid CR+PCR and CR+RD algorithms, which improve the performance of PCR, RD and CR by 21%, 31% and 61% respectively.
Proceedings ArticleDOI
Jasper: An End-to-End Convolutional Neural Acoustic Model.
Jason Li,Vitaly Lavrukhin,Boris Ginsburg,Ryan Leary,Oleksii Kuchaiev,Jonathan Cohen,Huyen Nguyen,Ravi Teja Gadde +7 more
TL;DR: This paper reports state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data and introduces a new layer-wise optimizer called NovoGrad to improve training.
Proceedings ArticleDOI
An interface for sketching 3D curves
TL;DR: This work presents a novel method for specifying 3D curves with 2D input from a single viewpoint that leverages skills that many artists and designers have developed from work with pencil and paper.
Posted Content
NeMo: a toolkit for building AI applications using Neural Modules.
Oleksii Kuchaiev,Jason Li,Huyen Nguyen,Oleksii Hrinchuk,Ryan Leary,Boris Ginsburg,Samuel Kriman,Stanislav Beliaev,Vitaly Lavrukhin,Jack Cook,Patrice Castonguay,Mariya Popova,Jocelyn Huang,Jonathan Cohen +13 more
TL;DR: NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition that provides built-in support for distributed training and mixed precision on latest NVIDIA GPUs.