Machine Learning Weekly Review №8
Nov 5, 2017 · 3 min read
mlreview.com — source of latest credible papers, videos and projects on machine learning for scientists and engineers.
Recommended this week
Projects
- Vega-Lite 2.0 — high-level language for rapidly creating interactive visualizations. Built by UW Interactive Data Lab.
- Tensorboard for PyTorch. Includes scalar, image, histogram, audio, text, graph and embedding.
- PyTorch-madrl — PyTorch impl of single and multi-agent RL algorithms (i.e A2C, ACKTR, DQN, DDPG, PPO)
- Colaboratory — interactive coding in your browser by Google Developers. More feature rich alternative to notebooks.azure.com.
- Gluon — imperative deep learning API from AWS and Microsoft based on MXNet.
- GPyOpt — Python library for Bayesian Optimization from Sheffield University.
- CoreMLTools — Protobuf serialization library for sklearn/caffe/keras/xgboost from Apple.
- CuPy — NumPy-compatible matrix library accelerated by CUDA.
- LM-LSTM-CRF — High-performance State-of-the-art Character-aware Sequence Labeling in PyTorch.
- Bambi – high-level Bayesian model-building interface in Python. Built by Tal Yarkoni on PyMC3.
- xgboostExplainer — R package that makes XGBoost as interpretable as single decision tree.
Research Papers
- “How deep learning works — The geometry of deep learning”. Finds its analogies with geometry of quantum computations and the diffeomorphic template matching.
- “Dynamic Routing Between Capsules”. CapsNet — new twist on neural network by Geoff Hinton that better at generalizing.
- “One pixel attack for fooling deep neural networks”. Affects 73.8% of test images with 98.7% confidence.
- “Progressive Growing of GANs for Improved Quality, Stability, and Variation”. NVIDIA AI generates CELEBA images at 1024x1024px.
- “Generative Adversarial Networks: An Overview”.
- “Understanding Generalization and Stochastic Gradient Descent”. Explores “generalization gap” & optimum batch size.
- “TFX: A TensorFlow-Based Production-Scale Machine Learning Platform”.
- “Rainbow: Combining Improvements in Deep Reinforcement Learning” by DeepMind.
- “Learning Diverse Skills via Maximum Entropy Deep RL” on multimodal learning in RL by UC Berkeley.
- “Unsupervised Machine Translation Using Monolingual Corpora Only”. Report 32.8 BLEU score without any parallel sentence at training time.
Posts, Articles, Tutorials
- “The State of Data Science & Machine Learning”. An industry-wide survey by Kaggle based on 16,000 responses.
- “Approaching (Almost) Any NLP Problem on Kaggle”.
- “Out-of-sample prediction for linear model with missing data” by Junpeng Lao using PyMC3.
- “Word embeddings in 2017: Trends and future directions” by Sebastian Ruder.
- “How Adversarial Attacks Work” by Roman Trusov.
- “Bayesian Decision Theory Made Ridiculously Simple”.
- “Selected papers structured by NLP task” by Kyubyong Park.
- “Colorizing B&W Photos with Neural Networks” by Emil Wallnér.
- “Speech Recognition Is Not Solved” I.e. accents and noise, semantic errors, multiple speakers etc.
- “The End of Human Doctors — The Bleeding Edge of Medical AI Research”.
- “Probabilistic programming: an annotated bibliography”.
Video Lectures and Talks
- “PyTorch Zero to All Crash Course” by Sung Hu Kim. Slides. Code.
- “Recent Advances, Frontiers and Future of Deep RL”. Talk at UC Berkeley Deep RL Bootcamp by DeepMind instructor.
- “Hands-on PyTorch workshop” by Luca Antiga Soumith Chintala.
- Video walkthrough of each chapter of “Deep Learning Book” by Ian Goodfellow.
- “Information Theory of Deep Learning” talk by Prof. Naftali Tishby at Yandex.
- “PyTorch: Fast Differentiable Dynamic Graphs in Python” by Soumith Chintala.
- Videos from Cognitive Computational Neuroscience (CCN) 2017.
- “Deep learning and Backprop in the Brain” by Yoshua Bengio CCN2017.
Free Books
- “Introduction to High-Performance Scientific Computing” by Victor Eijkhout. Contains both theory and practical tutorials.
You would also like
Facebook Group: Machine Learning Review
