ML sessions 2018

Interpretable ML #2 - 15. Nov. 2018 Why should i trust you?: Explaining the predictions of any classifier.

https://arxiv.org/pdf/1602.04938v1.pdf

Interpretable ML #1 - 1. Nov. 2018 Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning

https://arxiv.org/pdf/1806.00069.pdf

RNNs #5 - Applications - 18. Oct. 2018 Show, Attend and Tell: Neural Image Caption Generation with Visual Attention Sofia Explainable Neural Computation via Stack Neural Module Networks Judith Pixel Recurrent Neural Networks Federico Matteo Deep Variational Reinforcement Learning for POMDPs (ICML2018) Rika Wisture: RNN-based Learning of Wireless Signals for Gesture Recognition in Unmodified Smartphones Sahar Dong Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN) Louise A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues Samuel Maakus Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition Sarah Sanne Wavenet: A Generative Model for Raw Audio Isac Recurrent Neural Network for Multivariate Time Series with Missing Values Ruibo RNNs #5 - 04. Oct. 2018 Sequential Neural Models with Stochastic Layers

http://papers.nips.cc/paper/6039-sequential-neural-models-with-stochastic-layers.pdf

RNNs #4 - 20. Sep. 2018 An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

https://arxiv.org/pdf/1803.01271.pdf

RNNs #3 - 06. Sep. 2018 Neural Turing Machines

https://arxiv.org/pdf/1410.5401.pdf

RNNs #2 - 14. June. 2018 Sequence modeling: Recurrent and recursive nets (page: 388-415)

http://www.deeplearningbook.org/contents/rnn.html

RNNs #1 - 31. May. 2018 Sequence modeling: Recurrent and recursive nets (page: 367-388)

http://www.deeplearningbook.org/contents/rnn.html

-------------------------------------------------------------------------------- Something else - 17. May. 2018 The limits and potentials of deep learning for robotics

http://journals.sagepub.com/doi/full/10.1177/0278364918770733

Optimization for ML #5 - 03. May. 2018 The Supervised Learning No-Free-Lunch Theorems

web.mit.edu/6.435/www/Dempster77.pdf

Optimization for ML #5 - 19. Apr. 2018 Maximum Likelihood from Incomplete Data via the EM Algorithm

http://web.mit.edu/6.435/www/Dempster77.pdf

Optimization for ML #3 - 05. Apr. 2018 Sharp Minima Can Generalize For Deep Nets

https://arxiv.org/pdf/1703.04933.pdf

Optimization for ML #2 - 08. Mar. 2018 Support Vector Machines

http://cs229.stanford.edu/notes/cs229-notes3.pdf

Optimization for ML #1 - 22. Feb. 2018 Large-Scale Machine Learning with Stochastic Gradient Descent

https://link.springer.com/content/pdf/10.1007%2F978-3-7908-2604-3_16.pdf

-------------------------------------------------------------------------------- Probabilistic Deep Learning #6 - 08. Feb. 2018 Application Session

* Bayesian Recurrent Neural Networks
* Learning & policy search in stochastic dynamical systems with BNNs
* Deep Probabilistic Programming
* Neural Discrete Representation Learning
* Deep Bayesian Active Learning with Image Data
Probabilistic Deep Learning #5 - 25. Jan. 2018 Weight Uncertainty in Neural Networks

http://proceedings.mlr.press/v37/blundell15.pdf

Probabilistic Deep Learning #4 - 11. Jan. 2018 Priors for infinite networks

https://link.springer.com/content/pdf/10.1007%2F978-1-4612-0745-0_2.pdf

Probabilistic Deep Learning #3 - 14. Nov. 2017 Deep Kernel Learning¶ http://proceedings.mlr.press/v51/wilson16.pdf¶ Probabilistic Deep Learning #2 - 30. Nov. 2017 What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?¶ https://arxiv.org/pdf/1703.04977.pdf¶ Probabilistic Deep Learning #1 - 16. Nov. 2017 Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning¶ https://arxiv.org/abs/1506.02142¶ -------------------------------------------------------------------------------- State-of-the-art ML #5 - 02. Nov. 2017 Learning from Simulated and Unsupervised Images through Adversarial Training¶ https://arxiv.org/abs/1612.07828¶ State-of-the-art ML #4 - 19. Oct. 2017 "Why Should I Trust You?": Explaining the Predictions of Any Classifier¶ https://arxiv.org/abs/1602.04938.pdf¶ State-of-the-art ML #3 - 05. Oct. 2017 Balancing information exposure in social networks¶ https://arxiv.org/pdf/1709.01491.pdf¶ State-of-the-art ML #2 - 21. Sep. 2017 The numerics of GAN¶ https://arxiv.org/pdf/1705.10461.pdf¶ State-of-the-art ML #1 - 07. Sep. 2017 Deep Gaussian Processes¶ http://proceedings.mlr.press/v31/damianou13a.pdf​¶ -------------------------------------------------------------------------------- Inference in Bayesian Networks #6 - 29. June 2017
* Fast nonparametric clustering of structured time-series" by James Hensman, Magnus Rattray and Neil D. Lawrence - Olga
* Deep Gaussian Process Andreas, C. Damianou and Neil D. Lawrence - Judith
* Pitkow, X., & Angelaki, D. E. (2017). How the Brain Might Work: Statistics Flowing in Redundant Population Codes. - Ylva
Inference in Bayesian Networks #5 - 15. June 2017 An Introduction to MCMC for Machine Learning - C. Andrieu - ‎2003¶ http://mathfaculty.fullerton.edu/sbehseta/Math470-10.1.1.13.7133.pdf¶ Inference in Bayesian Networks #4 - 01. June 2017 Approximate Bayesian computational methods¶ http://link.springer.com/article/10.1007%2Fs11222-011-9288-2?LI=true¶ Inference in Bayesian Networks #3 - 18. May 2017 Hierarchical Beta Processes and the Indian Buffet Process (Monte Carlo inference scheme)¶ http://people.ee.duke.edu/~lcarin/thibaux-jordan-aistats07.pdf¶ Inference in Bayesian Networks #2 - 04. May 2017 Expectation Propagation for approximate Bayesian inference¶ https://arxiv.org/abs/1301.2294¶ Inference in Bayesian Networks #1 - 20. Apr. 2017 Understanding Belief Propagation and its Generalizations¶ http://www.merl.com/publications/docs/TR2001-22.pdf¶ -------------------------------------------------------------------------------- Transfer Learning #6 - 05. Apr. 2017 Application session Marcus and Judith"Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping"¶ Vladimir and Ondrej"Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning"¶ Sahar"Domain Randomization for transferring deep neural networks from simulations to real world"¶ Silvia and Erik"Effective Transfer Learning of Affordances for Household Robots"¶ Taras and Joonatan"Sim-to-Real Robot Learning from Pixels with Progressive Nets"¶ Olga"Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks"¶ Ylva and Ramon"How Transferable Are Features in Deep Neural Networks"¶ Transfer Learning #5 - 23. Mar. 2017 A theory of learning from different domains¶ http://www.alexkulesza.com/pubs/adapt_mlj10.pdf¶ Transfer Learning #4 - 9. Mar. 2017 Understanding deep learning requires rethinking generalization¶ https://arxiv.org/pdf/1611.03530¶ Transfer Learning #3 - 23. Feb. 2017 DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition¶ http://jmlr.org/proceedings/papers/v32/donahue14.pdf¶ Transfer Learning #2 - 9. Feb. 2017 Learning to learn by gradient descent by gradient descent¶ https://arxiv.org/abs/1606.04474¶ Transfer Learning #1 - 25. Jan. 2017 A Survey on Transfer Learning¶ https://www.cse.ust.hk/~qyang/Docs/2009/tkde_transfer_learning.pdf¶ ---------------------------------------------------------------------------------- Approximate inference #6 - 12. Jan. 2017 Black-Box Variational Inference¶ http://www.cs.columbia.edu/~blei/papers/RanganathGerrishBlei2014.pdf¶ Approximate inference #5 - 15. Dec. 2016 - Christmas edition Variational Tempering ¶ http://jmlr.org/proceedings/papers/v51/mandt16.pdf¶ Approximate inference #4 - 24. Nov. 2016 Variational Message Passing ¶ http://www.jmlr.org/papers/volume6/winn05a/winn05a.pdf¶ Approximate inference #3 - 10. Nov. 2016 Stochastic Variational Inference¶ http://jmlr.org/papers/volume14/hoffman13a/hoffman13a.pdf¶ Approximate inference #2 - 27. Oct. 2016 An Introduction to Variational Methodsfor Graphical Models¶ https://people.eecs.berkeley.edu/~jordan/papers/variational-intro.pdf¶ Approximate inference #1 - 13. Oct. 2016 Graphical Models¶ https://www.cs.cmu.edu/~aarti/Class/10701/readings/graphical_model_Jordan.pdf¶ ---------------------------------------------------------------------------------- Deep Learning #10 - 29. Sep. 2016 Deep learning application session Deep Learning #9 - 15. Sep. 2016 Learning to Communicate withDeep Multi-Agent Reinforcement Learning¶ https://arxiv.org/pdf/1605.06676v2.pdf¶ Deep Learning #8 - 23 June 2016 / 01. Sep. 2016 End-to-End Training of Deep Visuomotor Policies¶ https://arxiv.org/pdf/1504.00702v5.pdf¶ Deep Learning #7 - 9 June 2016 Benchmarking Deep Reinforcement Learning for Continuous Control¶ http://arxiv.org/pdf/1604.06778v2.pdf¶ Continuous control with deep reinforcement learning¶ http://arxiv.org/pdf/1509.02971v5.pdf¶ Deep Learning #6 - 26 May 2016 Playing atari with deep reinforcement learning ¶ http://arxiv.org/abs/1312.5602¶ Mastering the game of Go with deep neural networks and tree search¶ http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html¶ Deep Learning #5 - 12 May 2016 Variational Auto-encoded Deep Gaussian Processes http://arxiv.org/abs/1511.06455¶ Deep Learning #4 - 21 April 2016 Long Short-Term Memory Deep Learning #3 - 7 April 2016 ADVERSARIAL AUTOENCODERS- Goodfellow et.al (2016)¶ Deep Learning #2 - 24 March 2016 Represenation Learning: A Review and New Perspectives - Vincent et. al. (2014)¶ Deep Learning #1 - 10 March 2016 Deep Learning - Hinton et. al. (Nature, 2015)¶ ---------------------------------------------------------------------------------- Applications of Probabilistic Numerics and Bayesian Optimization (25 February 2016) Jim Holmström, Erik Ward:"Designing Engaging Games Using Bayesian Optimization"Silvia Cruciani, Ali Ghadirzadeh:"A Bayesian Exploration-Exploitation Approach for Optimal Online Sensing and Planning with a Visually Guided Mobile Robot"Cheng Zhang, Judith Butepage:"Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction"¶ [IMAGE]Anastasiia Varav, João ... de Carvalho"Metrics for Probabilistic Geometries"¶ Yanxia Zhang, Puren Guler"Robots that can adapt like animals"¶ ¶ ¶