Recommended this week
- Vectorflow is a minimalist neural network library optimized for sparse data and single machine environments. Blog Post.
- Merlin — Open Source Neural Network Speech Synthesis System.
- Academicpages — ready-to-fork GitHub Pages template for Academic Personal Websites. By R. Stuart Geiger.
- TensorFire is a framework for running neural networks in the browser, accelerated by WebGL.
- Deeplearn.js — javasript hardware-accelerated machine learning library from Google Brain(Daniel Smilkov).
- “Interpretable Active Learning”. Presented at 2017 ICML Workshop. Expands on LIME framework.
- “ClothCap: Seamless 4D Clothing Capture and Retargeting”. Segments and tracks garment pieces and estimates body shape. Demo.
- “Learning to Reinforcement Learn”. Earns Prize for Applied Cognition at CogSci 2017.
- “Photographic Image Synthesis with Cascaded Refinement Networks”. Synthesizes photographic images at 2-megapixel resolution. TensorFlow code.
- “Causal Transfer Learning”. NIPS 2017. Generic method identifies sets of features that lead to transferable predictions.
- Proceedings of International Machine Learning Research (ICML 2017).
- “SmoothGrad: removing noise by adding noise” from Google Brain (Daniel Smilkov). PyTorch code.
- “A Beginner’s Guide to Optimizing Pandas Code for Speed” by Sofia Heisler.
- “A 2017 Guide to Semantic Segmentation with Deep Learning”.
- “Guides and best practices for effective use of Tensorflow” by Vahid Kazemi.
- A Step-by-Step Guide to Synthesizing Adversarial Examples. By Anish Athalye.
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…
Facebook Group: Machine Learning Review