Dieuwke Hupkes
Artificial Intelligence · 2016–2024
A researcher in the Science corpus: 18 papers; trusts 952 researchers and is trusted by 136 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 328 citations into it; #2,768 of 36,961 by trust here, #2,141 by citations
- Natural Language Processing — 205 citations into it; #792 of 5,725 by trust here, #1,119 by citations
- Model Architectures — 111 citations into it; #431 of 2,288 by trust here, #1,018 by citations
- Computer Vision and Pattern Recognition — 94 citations into it; #21,543 of 21,973 by trust here, #6,327 by citations
- Representation & Self-Supervised Learning — 44 citations into it; #2,382 of 3,156 by trust here, #2,367 by citations
- Cognitive Neuroscience — 38 citations into it
- Evaluation & Benchmarks — 35 citations into it
- Language and Linguistics — 32 citations into it
Whom Dieuwke Hupkes trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Ilya Sutskever
- Yoshua Bengio
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alex Graves
- Dzmitry Bahdanau
- Kyunghyun Cho
- Alex Krizhevsky
- Oriol Vinyals
- Sepp Hochreiter
Who trusts Dieuwke Hupkes overall
- Yonatan Belinkov
- John Hewitt
- Tal Linzen
- Abhilasha Ravichander
- Grzegorz Chrupała
- John Wieting
- Percy Liang
- Ofir Press
- Willem H. Zuidema
- R. Thomas McCoy
Papers from Dieuwke Hupkes's perspective
Ordered by how strongly the researchers Dieuwke Hupkes trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- 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
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- Compositionality Decomposed: How do Neural Networks Generalise? (2019) — 408 citations
- Visualisation and 'diagnostic classifiers' reveal how recurrent and recursive neural networks process hierarchical structure (2017) — 304 citations
- The Llama 3 Herd of Models (2024) — 17,085 citations
- Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information (2018) — 202 citations
- Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little (2021) — 297 citations
- The emergence of number and syntax units in LSTM language models (2019) — 190 citations
- Diagnostic Classifiers Revealing how Neural Networks Process Hierarchical Structure (2016) — 47 citations
- Location Attention for Extrapolation to Longer Sequences (2019) — 50 citations
- Analysing Neural Language Models: Contextual Decomposition Reveals Default Reasoning in Number and Gender Assignment (2019) — 42 citations
- Visualisation and 'Diagnostic Classifiers' Reveal how Recurrent and Recursive Neural Networks Process Hierarchical Structure (Extended Abstract) (2018) — 25 citations
- Proceedings of the 2018 EMNLP Workshop BlackboxNLP : Analyzing and Interpreting Neural Networks for NLP (2018) — 98 citations
- Mechanisms for handling nested dependencies in neural-network language models and humans. (2020) — 75 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2023) — 266 citations
- Compositionality Decomposed: How do Neural Networks Generalise? (Extended Abstract) (2020) — 29 citations
- Transcoding Compositionally: Using Attention to Find More Generalizable Solutions (2019) — 30 citations
- Learning compositionally through attentive guidance (2018) — 31 citations
- Diagnostic classification and symbolic guidance to understand and improve recurrent neural networks (2017)