Jason Yosinski
Artificial Intelligence · 2013–2023
A researcher in the Science corpus: 24 papers; trusts 1,950 researchers and is trusted by 7,188 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 409 citations into it; #586 of 36,961 by trust here, #424 by citations
- Computer Vision and Pattern Recognition — 328 citations into it; #483 of 21,973 by trust here, #261 by citations
- Natural Language Processing — 86 citations into it; #3,614 of 5,725 by trust here, #1,327 by citations
- Model Architectures — 72 citations into it; #631 of 2,288 by trust here, #569 by citations
- Generative Models — 67 citations into it; #236 of 1,963 by trust here, #279 by citations
- Representation & Self-Supervised Learning — 61 citations into it; #327 of 3,156 by trust here, #125 by citations
- Optimization & Training — 56 citations into it
- Probabilistic & Bayesian Methods — 45 citations into it; #969 of 1,526 by trust here, #781 by citations
Whom Jason Yosinski trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
- Kaiming He
- Matthew D. Zeiler
- Diederik P. Kingma
- Karen Simonyan
- Jia Deng
Who trusts Jason Yosinski overall
- Yoshua Bengio
- Wojciech Samek
- Mingsheng Long
- Maithra Raghu
- Andrea Vedaldi
- Jeff Clune
- Anh Totti Nguyen
- Trevor Darrell
- Mohit Bansal
- Bolei Zhou
Papers from Jason Yosinski's perspective
Ordered by how strongly the researchers Jason Yosinski 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- How transferable are features in deep neural networks? (2014) — 9,349 citations
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images (2014) — 3,543 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- Deep Generative Stochastic Networks Trainable by Backprop (2013) — 400 citations
- Understanding Neural Networks Through Deep Visualization (2015) — 1,959 citations
- Plug and Play Language Models: A Simple Approach to Controlled Text Generation (2019) — 1,229 citations
- Synthesizing the preferred inputs for neurons in neural networks via deep generator networks (2016) — 739 citations
- An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution (2018) — 1,041 citations
- Measuring the Intrinsic Dimension of Objective Landscapes (2018) — 566 citations
- Convergent Learning: Do different neural networks learn the same representations? (2015) — 435 citations
- Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation (2015) — 127 citations
- Supermasks in Superposition (2020) — 352 citations
- Metropolis-Hastings Generative Adversarial Networks (2018) — 109 citations
- Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask (2019) — 426 citations
- GSNs : Generative Stochastic Networks (2015) — 50 citations
- SVCCA: Singular Vector Canonical Correlation Analysis for Deep Understanding and Improvement (2017) — 36 citations
- Language Models are Few-shot Multilingual Learners (2021) — 173 citations
- Hamiltonian Neural Networks (2019) — 1,264 citations
- Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks (2016) — 357 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2023) — 266 citations