TRFL : TensorFlow Reinforcement Learning
A library of reinforcement learning building blocks
By DeepMind: https://github.com/deepmind/trfl
#DeepLearning #TensorFlow #ReinforcementLearning

Efficient Graph Generation with Graph Recurrent Attention Networks
Liao et al.: https://arxiv.org/abs/1910.00760
Code: https://github.com/lrjconan/GRAN
#Graph #NeuralNetworks #NeurIPS #NeurIPS2019

Language Models as Knowledge Bases?
Petroni et al.: https://arxiv.org/abs/1909.01066
#Transformers #NaturalLanguageProcessing #MachineLearning

Fine tuning U-Net for ultrasound image segmentation: which layers?. http://arxiv.org/abs/2002.08438

Machine learning identifies variability among children's neural anatomy


http://sciencemission.com/site/index.php

MonoLayout: Amodal scene layout from a single image
Paper: https://arxiv.org/pdf/2002.08394.pdf
Github: https://hbutsuak95.github.io/monolayout/

Introduction to Reinforcement Learning
By DeepMind: https://www.youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZDM- OYHWgPebj2MfCFzFObQ
#DeepLearning #ReinforcementLearning #Robotics

MIT Deep Learning online course *New 2020 Edition* ALL! New lectures every week for the rest of the course with slides, video coding labs
For all lectures, slides, and lab materials http://introtodeeplearning.com/

https://www.youtube.com/watch?v=iaSUYvmCekI&feature=youtu.be

Using neural networks to solve advanced mathematics equations
https://ai.facebook.com/blog/using-neural-networks-to-solve-advanced-mathematics-equations/

Best Practices for Machine Learning engineering

https://github.com/mukeshmithrakumar/Book_List/blob/master/Rules%20of%20Machine%20Learning.pdf

The Global Expansion of AI Surveillance
https://carnegieendowment.org/2019/09/17/global-expansion-of-ai-surveillance-pub-79847

KaoKore: A Pre-modern Japanese Art Facial Expression Dataset
Paper: https://arxiv.org/pdf/2002.08595v1.pdf
Github: https://github.com/rois-codh/kaokore

Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer
we present a large-scale empirical survey to determine which transfer learning techniques work best and apply these insights at scale to create a new model that we call the Text-To-Text Transfer Transformer (T5). We also introduce a new open-source pre-training dataset, called the Colossal Clean Crawled Corpus (C4). The T5 model, pre-trained on C4, achieves state-of-the-art results on many NLP benchmarks while being flexible enough to be fine-tuned to a variety of important downstream tasks. In order for our results to be extended and reproduced, we provide the code and pre-trained models, along with an easy-to-use Colab Notebook to help get started.
https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html

Intro to Graph Representation Learning

The simple PyTorch implementations along with the easy explanations are good to get one started.

The following repository holds the code and link to the blogs, by Data Science Group, IIT Roorkee : https://github.com/dsgiitr/graph_nets

250,000 Cars - Top 10 Free Vehicle Image and Video Datasets for Machine Learning
https://lionbridge.ai/datasets/250000-cars-top-10-free-vehicle-image-and-video-datasets-for-machine-learning/

oIRL: Robust Adversarial Inverse Reinforcement Learning with Temporally Extended Actions. http://arxiv.org/abs/2002.09043

New Kaggle Competition: University of Liverpool - Ion Switching - Identify the number of channels open at each time point. Total Prize of $25,000.

https://www.kaggle.com/c/liverpool-ion-switching