Dietrich Klakow

Artificial Intelligence · 2002–2020

A researcher in the Science corpus: 13 papers; trusts 1,582 researchers and is trusted by 31 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 430 citations into it; #6,353 of 35,345 by trust here, #9,092 by citations
• Computer Vision and Pattern Recognition — 350 citations into it
• Natural Language Processing — 233 citations into it; #2,457 of 5,688 by trust here, #3,977 by citations
• Multimodal Learning — 140 citations into it
• Evaluation & Benchmarks — 66 citations into it
• Safety, Robustness & Interpretability — 52 citations into it
• Model Architectures — 41 citations into it
• Large Language Models — 40 citations into it; #261 of 799 by trust here, #561 by citations

Whom Dietrich Klakow trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Kaiming He
4. Alex Krizhevsky
5. Diederik P. Kingma
6. Ilya Sutskever
7. Yann LeCun
8. Karen Simonyan
9. Ross B. Girshick
10. Alex Graves

Who trusts Dietrich Klakow overall

1. Alexander J. Ratner
2. Zhijian Ou
3. Paroma Varma
4. Mengqiu Wang
5. Stephen H. Bach
6. Chien-Yi Chang
7. Christopher R'e
8. Yaofang Liu
9. Dan Shen
10. Steven Bethard

Papers from Dietrich Klakow's perspective

Ordered by how strongly the researchers Dietrich Klakow trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• Testing the correlation of word error rate and perplexity (2002) — 278 citations
• Exploring Correlation of Dependency Relation Paths for Answer Extraction (2006) — 60 citations
• Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence (2020) — 51 citations
• A Batch Noise Contrastive Estimation Approach for Training Large Vocabulary Language Models (2017) — 6 citations
• Combining Generative and Discriminative Model Scores for Distant Supervision (2013) — 44 citations
• A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2020) — 396 citations
• Logit Pairing Methods Can Fool Gradient-Based Attacks (2018) — 87 citations
• On the security relevance of weights in deep learning. (2020)
• On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines (2020) — 475 citations
• Investigating the Impact of Pre-trained Word Embeddings on Memorization in Neural Networks (2020) — 39 citations
• Adversarial Initialization - when your network performs the way I want (2019) — 8 citations
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods (2019) — 148 citations
• The Extended SPaRKy Restaurant Corpus: Designing a Corpus with Variable Information Density (2017) — 7 citations