Recommended this week
- Ncnn is a high-performance neural network inference framework from Tencent. Optimized for the mobile platform and edge computing.
- art-DCGAN — Modified version of DCGAN with a focus on generating artworks by Robbie Barrat.
- Beholder — A TensorBoard plugin for visualizing arbitrary tensors in a video as your network trains.
- Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
- AsciiMath is an easy-to-write markup language for mathematics. LaTeX alternative that works in a Browser.
- ChainerCV – a Library for Computer Vision in Deep Learning.
- AudioSet — alarge-scale dataset of manually annotated audio events by Google Developers.
- Tslearn — Python package for the time series analysis.
- text2vec — fast vectorization, topic modeling, distances and GloVe word embeddings in R.
- “Filtering Variational Objectives”. Uses a particle filter to form a tighter bound then ELBO. ICML2017.
- “PGAN — Probabilistic Generative Adversarial Networks” by Hamid. NIPS 2017 Submission.
- “A Neural Parametric Singing Synthesizer”. Allows conveniently modify pitch to match any target melody.
- “Unbiased Markov chain Monte Carlo with Couplings”. With unbiased MCMC we can compute R estimators in parallel and take their average. Blog Post.
- “Uncertainty in Deep Learning”. PhD Thesis by Yarin Gal. Research Fellow at University of Cambridge.
- “Create Anime Characters with A.I.” Based on DRAGAN. Technical Report. Demo.
- “Sound-Word2Vec: Learning Word Representations Grounded in Sounds”. Accepted at EMNLP 2017.
- “What Actions are Needed for Understanding Human Actions in Video?”. ICCV2017. Code.
- “Semantic Instance Segmentation with a Discriminative Loss Function”. CVPR2017.
- “SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis”. Takes a set of images and their corresponding camera parameters as input and directly infers the 3D model. ICCV 2017 Poster.
- “Understanding Black-box Predictions via Influence Functions”. Explains black-box model by requiring only an oracle access to gradients and Hessian-vector products. ICML2017. Code.
- “Exploiting the Natural Exploration In Contextual Bandits”. Greedy-First — outperforms exploration-based contextual bandit algorithms Thompson sampling, UCB, or ϵ-greedy.
- “Deep Learning for NLP Best Practices” by Sebastian Ruder.
- “Gentle introduction to the Bregman divergences” by Mark Reid.
- “Predictive Vision In A Nutshell” by Filip Piekniewski.
- “Graph Convolutional Networks” by Thomas Kipf.
- “How I Used Deep Learning To Train A Chatbot To Talk Like Me” by Adit Deshpande.
- “Building Mobile Applications with TensorFlow” free book by Pete Warden.
- Introduction to Artificial Neural Networks and Deep Learning. A Practical Guide with Applications in Python ebook by Sebastian Raschka.
- “Python Data Science Handbook” in the form of Jupyter notebooks.
- ”Convolutional Neural Networks for Visual Recognition” lectures by Stanford University.
- HarvardX Biomedical Data Science Open Online Training. Videos and Code for “Genomics Data Analysis Series”, “Using Python for Research” Courses.
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