Paolo Frasconi
Artificial Intelligence · 1993–2018
A researcher in the Science corpus: 14 papers; trusts 225 researchers and is trusted by 3,038 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 106 citations into it; #456 of 36,961 by trust here, #1,175 by citations
- Computational Theory and Mathematics — 31 citations into it; #7,088 of 12,489 by trust here, #4,101 by citations
- Optimization & Training — 31 citations into it; #1,532 of 2,605 by trust here, #1,574 by citations
- Computer Vision and Pattern Recognition — 28 citations into it; #9,743 of 21,973 by trust here, #9,217 by citations
- Molecular Biology — 20 citations into it; #4,430 of 17,836 by trust here, #6,868 by citations
- Representation & Self-Supervised Learning — 20 citations into it; #1,024 of 3,156 by trust here, #1,724 by citations
- Model Architectures — 18 citations into it; #156 of 2,288 by trust here, #150 by citations
- Natural Language Processing — 12 citations into it; #4,506 of 5,725 by trust here, #5,539 by citations
Whom Paolo Frasconi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Diederik P. Kingma
- Ronald J. Williams
- Alex Krizhevsky
- Kaiming He
- Yann LeCun
- Ilya Sutskever
- Radford M. Neal
- J. Urgen Schmidhuber
Who trusts Paolo Frasconi overall
- Yoshua Bengio
- Kyunghyun Cho
- J. Urgen Schmidhuber
- Sergey Levine
- Quoc V. Le
- Ruslan Salakhutdinov
- Yann LeCun
- Dacheng Tao
- Richard Socher
- Trevor Darrell
Papers from Paolo Frasconi's perspective
Ordered by how strongly the researchers Paolo Frasconi 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
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Learning long-term dependencies with gradient descent is difficult (1994)
- Forward and Reverse Gradient-Based Hyperparameter Optimization (2017) — 477 citations
- A general framework for adaptive processing of data structures (1998)
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning (2018) — 888 citations
- The problem of learning long-term dependencies in recurrent networks (1993)
- Towards Incremental Parsing of Natural Language Using Recursive Neural Networks (2003) — 65 citations
- Graph Invariant Kernels (2015) — 136 citations
- Exploiting the past and the future in protein secondary structure prediction (1999)
- DISULFIND: a disulfide bonding state and cysteine connectivity prediction server (2006) — 348 citations
- Classification of small molecules by two- and three-dimensional decomposition kernels (2007) — 36 citations
- Prediction of protein beta-residue contacts by Markov logic networks with grounding-specific weights (2009) — 66 citations
- Learning Influence among Interacting Markov Chains (2005) — 260 citations
- Fingerprint Classification with Combinations of Support Vector Machines (2001) — 78 citations
- An Input Output HMM Architecture (1994)