# Machine Learning Weekly Review №7

mlreview.com — the s*ource of latest credible papers, videos and projects on machine learning for scientists and engineers.*

### Recommended this week

#### Projects

- Mcmc-demo – interactive dashboard Deep Learning (DLSS) and Reinforcement Learning (RLSS) Summer School, Montreal 2017 various MCMC sampling algorithms.
- Kaldi — Speech Recognition Toolkit. Offers TensorFlow integration.
- Tensorflow and PyTorch implementations of 9 Generative Adversarial Networks (LSGAN, WGAN, DRAGAN, InfoGAN etc).
- AWD-LSTM — implementation of state-of-the-art Language Modeling in PyTorch. From Salesforce (Stephen Merity).
- Fashion-MNIST — A drop-in replacement of the original MNIST dataset.
- Nnabla — Neural Network Libraries by Sony. Python API, Dynamic computation graph, Multi-platform, Multi-GPU.
- Foolbox — Python toolbox to create adversarial examples that fool neural networks. Supports TF, PyTorch, MxNet etc.

#### Research Papers

- “Neural Machine Translation and Sequence-to-sequence Models: A Tutorial”. Does not assume any particular experience with neural networks or natural language processing from a reader. 65pp.
- “Deep Learning for Video Game Playing” Survey by Niels Justesen. Reviews recent Deep Learning advances in a context of different types of games: shooter, strategy, arcade.
- “Personalizing Session-based Recommendations with Hierarchical RNN” ACM RecSys 2017 paper by Massimo Quadrana with code.
- “The prior can generally only be understood in the context of the likelihood”. Addresses paradox that although true prior should be independent of a model, in practice it’s usually motivated by likelihood.
- “Reinforcement Learning with a Corrupted Reward Channel”. No real-world reward function is perfect and how to deal with it. By Tom Everitt, Victoria Krakovna, Laurent Orseau.
- “TheoSea: Marching Theory to Light”. Can computer given VE figure out mathematically compact theories? TheoSea rediscovers Maxwell equations.
- “UE4Sim: A Photo-Realistic Simulator for Computer Vision Applications”. Built on top of the Unreal Engine.
- “Learning Transferable Architectures for Scalable Image Recognition”. ImageNet SOTA: 0.8% more and 9bln FLOPS less.
- “Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints”. EMNLP 2017 Award.

#### Posts, Articles, Tutorials

- “Ensemble Learning to Improve Machine Learning Results”. How ensemble methods work: bagging, boosting and stacking. By Vadim Smolyakov.
- “Background removal with deep learning” by Gidi Shperber.
- “10 Deep Learning projects based on Apache MXNet” by Julien Simon.
- “Getting Inception Architectures to Work with Style Transfer” by Sahil Singla.
- “An Alternative to Sgd: Stochastic Variance Reduction Methods”.
- “How to Train a Simple Audio Recognition Network” in Tensorflow by Pete Warden.
- “Tutorial — What is a variational autoencoder?”.
- Line-by-line Preprocessing Walkthrough for winning Data Science Bowl Submission by Brad Kenstler.
- “Python For Finance: Algorithmic Trading” by Karlijn Willems.
- “How does physics connect to machine learning?”
- “5 Heroic Python NLP Libraries”: NLTK, TextBlob, Stanford CoreNLP, spaCy, gensim.
- “StarCraft II RL Tutorial 1”. Deepmind’s StarCraft II RL Environment.

#### Free Books

- “Speech and Language Processing (3rd ed. draft)” — a leading textbook for natural language processing by Stanford Prof. Dan Jurafsky and Prof. James H. Martin.
- “Computer Age Statistical Inference: Algorithms, Evidence and Data Science” by Stanford Prod. Bradley Efron.

#### Video Lectures and Talks

- “Deep Learning for Self-Driving Cars” lectures and slides from MIT.
- “Pixel GAN autoencoder” talk by Alireza Makhzani. Slides.
- Deep Learning (DLSS) and Reinforcement Learning (RLSS) Summer School, Montreal 2017.
- JupyterCon Talks Recordings.
- “Deep Learning for Natural Language Processing” Course by Oxford University. Features videos, slides and recommended reading.
- “An Introduction to Deep Learning with TensorFlow” talk by Sebastian Raschka
- “What is wrong with convolutional neural nets?” by Geoffrey Hinton at Fields Institute, 2017

### You would also like

**ML Review (@ml_review) | Twitter**

*The latest Tweets from ML Review (@ml_review). We cover latest Research in Machine Learning, including Papers, Video…*twitter.com

Facebook Group: Machine Learning Review