Hamiltonian Graph Networks with ODE Integrators
Sanchez-Gonzalez et al.: https://arxiv.org/abs/1909.12790
#ArtificialIntelligence #Hamiltonian #GraphNetworks

Bayesian Deep Learning Benchmarks
Oxford Applied and Theoretical Machine Learning Group : https://github.com/OATML/bdl-benchmarks
#Bayesian #Benchmark #DeepLearning

We’ve completed the first fastMRI image reconstruction challenge to spur development of new AI techniques to make scans 10x faster. Congratulations to the top entrants, who’ve been invited to present at the Medical Imaging Meets NeurIPS workshop!

https://ai.facebook.com/blog/results-of-the-first-fastmri-image-reconstruction-challenge

We just released our #NeurIPS2019 Multimodal Model-Agnostic Meta-Learning (MMAML) code for learning few-shot image classification, which extends MAML to multimodal task distributions (e.g. learning from multiple datasets). The code contains #PyTorch implementations of our model and two baselines (MAML and Multi-MAML) as well as the scripts to evaluate these models to five popular few-shot learning datasets: Omniglot, Mini-ImageNet, FC100 (CIFAR100), CUB-200-2011, and FGVC-Aircraft.

Code: https://github.com/shaohua0116/MMAML-Classification

Paper: https://arxiv.org/abs/1910.13616

#NeurIPS #MachineLearning #ML #code

Mathematics for Machine Learning

Free Download Printed Book Cambridge University Press
https://mml-book.github.io/


#artificialintelligence #AI #Mathematics #calculus #linearalgebra #deeplearning #machinelearning

Single Headed Attention RNN: Stop Thinking With Your Head
Stephen Merity : https://arxiv.org/abs/1911.11423
#ArtificialIntelligence #NeuralComputing #NLP

Pre-Debate Material :
"BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop"
Maxime Chevalier-Boisvert et al.:
https://arxiv.org/abs/1810.08272v2
#AIDebate #MontrealAI #ReinforcementLearning

Datasets: 23,000 NHS Doctor Jobs Postings
Download: https://www.kaggle.com/homelesssandwich/nhs-jobs

Dive into Deep Learning (Book) by Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola
Download Link: https://d2l.ai/d2l-en.pdf
Github: https://github.com/d2l-ai/d2l-en
STAT 157, UC Berkeley: https://courses.d2l.ai/berkeley-stat-157/index.html

Introducing TensorBoard.dev: a new way to share your ML experiment results
Blog by Gal Oshri : https://blog.tensorflow.org/2019/12/introducing-tensorboarddev-new-way-to.html
#ArtificialIntelligence #MachineLearning #TensorFlow

GNNExplainer: Generating Explanations for Graph Neural Networks
Ying et al. : https://arxiv.org/abs/1903.03894
Code : https://github.com/RexYing/gnn-model-explainer
#ArtificialIntelligence #Graph #NeuralNetworks

Single Sample Feature Importance: An Interpretable Algorithm for Low-Level Feature Analysis. https://arxiv.org/abs/1911.11901

AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adver... https://arxiv.org/abs/1911.11897

Visual Physics: Discovering Physical Laws from Videos. https://arxiv.org/abs/1911.11893

What's Hidden in a Randomly Weighted Neural Network? by Ali Farhadi, Mohammad Rastegari , Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi,
Ramanujan et al.: https://arxiv.org/abs/1911.13299
#Artificialintelligence #DeepLearning #MachineLearning join https://t.iss.one/ArtificialIntelligenceArticles

Animesh Karnewar :

We are releasing the new version of our MSG-GAN work. https://arxiv.org/abs/1903.06048 today.

Code at https://github.com/akanimax/msg-stylegan-tf.

We present much better experimental evaluation of the method and also incorporate the Multi-scale modifications in stylegan. It was an honor collaborating with Oliver Wang. Special thanks to Alexia Jolicoeur-Martineau and Michael Hofmann for the encouragement and support.

We also experiment with our newly created (Indian Celebs) dataset (very small 3K) and get very nice results.

Please do check it out. Any feedback / suggestions are most welcome.

Fast Task Inference with Variational Intrinsic Successor Features
A novel algorithm that learns controllable features that can be leveraged to provide enhanced generalization and fast task inference through the successor feature framework.
The fundamental problem they face is a need to generalize between different latent codes, a task to which neural networks alone seem poorly suited.
To solve this generalization and slow inference problem by making use of successor features
To show that variational-intrinsic-control/diversity-is-all-you-need algorithms can be adapted to learn precisely the features needed by successor features
PAPER
https://arxiv.org/pdf/1906.05030.pdf

Probing the State of the Art: A Critical Look at Visual Representation Evaluation
Resnick et al.: https://arxiv.org/abs/1912.00215
#ArtificialIntelligence #DeepLearning #MachineLearning