Souhaib Ben Taieb

Artificial Intelligence · 2010–2016

A researcher in the Science corpus: 5 papers; trusts 32 researchers and is trusted by 9 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 20 citations into it; #32,361 of 35,345 by trust here, #29,412 by citations
• Management Science and Operations Research — 19 citations into it; #4,149 of 11,946 by trust here, #2,539 by citations
• Statistics and Probability — 16 citations into it
• Statistical Learning Theory — 14 citations into it
• Economics and Econometrics — 13 citations into it
• Electrical and Electronic Engineering — 12 citations into it; #11,967 of 16,539 by trust here, #10,998 by citations
• Optimization & Training — 10 citations into it
• Computer Vision and Pattern Recognition — 6 citations into it

Whom Souhaib Ben Taieb trusts overall

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

1. Paul J. Werbos
2. Jerome H. Friedman
3. Trevor J. Hastie
4. Shu Fan
5. Antti Sorjamaa
6. Robert Tibshirani
7. Andreas S. Weigend
8. Robert E. Schapire
9. Christopher G. Atkeson
10. James Franklin

Who trusts Souhaib Ben Taieb overall

1. Georgia A. Papacharalampous
2. Kasun Bandara
3. Amir F. Atiya
4. Ruofeng Wen
5. Bryan Lim
6. Christoph Bergmeir
7. Devon K. Barrow
8. Hansika Hewamalage
9. Nikolaos Kourentzes
10. Alberto Gasparin

Papers from Souhaib Ben Taieb's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Bagging Predictors
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
5. Regression Shrinkage and Selection via the Lasso
6. Gradient-based learning applied to document recognition
7. The Nature of Statistical Learning Theory
8. Long Short-Term Memory
9. ImageNet: A large-scale hierarchical image database
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition (2011) — 700 citations
• Machine Learning Strategies for Time Series Forecasting (2012) — 545 citations
• Multiple-output modeling for multi-step-ahead time series forecasting (2010) — 240 citations
• A gradient boosting approach to the Kaggle load forecasting competition (2014) — 294 citations
• A Bias and Variance Analysis for Multistep-Ahead Time Series Forecasting (2016)