Jan Chorowski
Artificial Intelligence · 2012–2020
A researcher in the Science corpus: 17 papers; trusts 1,296 researchers and is trusted by 3,075 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 350 citations into it; #459 of 36,961 by trust here, #516 by citations
- Computer Vision and Pattern Recognition — 175 citations into it; #1,869 of 21,973 by trust here, #1,365 by citations
- Natural Language Processing — 136 citations into it; #483 of 5,725 by trust here, #468 by citations
- Signal Processing — 108 citations into it; #646 of 7,592 by trust here, #231 by citations
- Model Architectures — 96 citations into it; #254 of 2,288 by trust here, #184 by citations
- Speech & Audio — 77 citations into it; #23 of 1,080 by trust here, #25 by citations
- Optimization & Training — 43 citations into it; #1,362 of 2,605 by trust here, #552 by citations
- Representation & Self-Supervised Learning — 43 citations into it; #1,299 of 3,156 by trust here, #1,246 by citations
Whom Jan Chorowski trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Graves
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Ilya Sutskever
- Dzmitry Bahdanau
- Alex Krizhevsky
- Oriol Vinyals
- Yann LeCun
- Kyunghyun Cho
Who trusts Jan Chorowski overall
- Takaaki Hori
- Shinji Watanabe
- Wei-Ning Hsu
- Tara N. Sainath
- William Chan
- Yu Zhang
- Navdeep Jaitly
- Rohit Prabhavalkar
- Quoc V. Le
- Yoshua Bengio
Papers from Jan Chorowski's perspective
Ordered by how strongly the researchers Jan Chorowski trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Going deeper with convolutions
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Attention-Based Models for Speech Recognition (2015) — 2,769 citations
- Regularizing Neural Networks by Penalizing Confident Output Distributions (2017) — 1,268 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- End-to-end attention-based large vocabulary speech recognition (2015) — 1,207 citations
- End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results (2014) — 488 citations
- State-of-the-Art Speech Recognition with Sequence-to-Sequence Models (2017) — 1,190 citations
- Blocks and Fuel: Frameworks for deep learning (2015) — 188 citations
- Towards Better Decoding and Language Model Integration in Sequence to Sequence Models (2016) — 384 citations
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
- Task Loss Estimation for Sequence Prediction (2015) — 33 citations
- Sequence-to-Sequence Models Can Directly Translate Foreign Speech (2017) — 370 citations
- Robust 3D Action Recognition with Random Occupancy Patterns (2012) — 499 citations
- Unsupervised Speech Representation Learning Using WaveNet Autoencoders (2019) — 340 citations
- On Using Backpropagation for Speech Texture Generation and Voice Conversion (2017) — 19 citations
- A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning (2020) — 29 citations
- Input Switched Affine Networks: An RNN Architecture Designed for Interpretability (2016) — 38 citations
- Blocks and Fuel (2015)