Tapani Raiko
Artificial Intelligence · 2007–2016
A researcher in the Science corpus: 22 papers; trusts 883 researchers and is trusted by 3,607 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 218 citations into it; #461 of 36,961 by trust here, #1,827 by citations
- Computer Vision and Pattern Recognition — 112 citations into it; #1,267 of 21,973 by trust here, #1,767 by citations
- Probabilistic & Bayesian Methods — 90 citations into it; #267 of 1,526 by trust here, #310 by citations
- Optimization & Training — 68 citations into it; #529 of 2,605 by trust here, #912 by citations
- Representation & Self-Supervised Learning — 52 citations into it; #1,115 of 3,156 by trust here, #613 by citations
- Statistics and Probability — 45 citations into it
- Generative Models — 40 citations into it; #350 of 1,963 by trust here, #398 by citations
- Statistical and Nonlinear Physics — 24 citations into it; #1,017 of 10,175 by trust here, #2,141 by citations
Whom Tapani Raiko trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Ruslan Salakhutdinov
- Yoshua Bengio
- Yann LeCun
- Alex Krizhevsky
- Diederik P. Kingma
- Radford M. Neal
- Kyunghyun Cho
- Shun-ichi Amari
- Richard S. Sutton
Who trusts Tapani Raiko overall
- Yoshua Bengio
- Kyunghyun Cho
- Kaiming He
- Sergey Levine
- Ruslan Salakhutdinov
- Zhe Gan
- Trevor Darrell
- Quoc V. Le
- Aaron C. Courville
- Dacheng Tao
Papers from Tapani Raiko's perspective
Ordered by how strongly the researchers Tapani Raiko 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
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Semi-supervised Learning with Ladder Networks (2015) — 1,426 citations
- Ladder Variational Autoencoders (2016) — 1,005 citations
- Deep Learning Made Easier by Linear Transformations in Perceptrons (2012) — 209 citations
- Techniques for Learning Binary Stochastic Feedforward Neural Networks (2014) — 129 citations
- How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks (2016) — 142 citations
- Enhanced Gradient and Adaptive Learning Rate for Training Restricted Boltzmann Machines (2011) — 87 citations
- Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities (2013) — 34 citations
- Parallel tempering is efficient for learning restricted Boltzmann machines (2010) — 92 citations
- Enhanced Gradient for Training Restricted Boltzmann Machines (2013) — 67 citations
- Iterative Neural Autoregressive Distribution Estimator NADE-k (2014) — 41 citations
- Approximate Riemannian Conjugate Gradient Learning for Fixed-Form Variational Bayes (2010) — 114 citations
- Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters (2015) — 183 citations
- Natural Conjugate Gradient in Variational Inference (2007) — 51 citations
- A Two-Stage Pretraining Algorithm for Deep Boltzmann Machines (2013) — 26 citations
- Stochastic gradient estimate variance in contrastive divergence and persistent contrastive divergence (2013)
- Semi-supervised detection of collective anomalies with an application in high energy particle physics (2012) — 28 citations
- 33rd International Conference on Machine Learning, ICML 2016 (2016) — 10 citations
- International Conference on Learning Representations (ICLR) (2016) — 662 citations
- Self-organization and missing values in SOM and GTM (2015) — 118 citations
- Tikhonov-Type Regularization for Restricted Boltzmann Machines (2012) — 15 citations