The mathematics of machine learning and deep learning – Sanjeev Arora – ICM2018 https://goo.gl/vj2yCF @ArtificialIntelligenceArticles

Why building your own Deep Learning computer is 10x cheaper than AWS

https://goo.gl/4ZbUf8 @ArtificialIntelligenceArticles

Speech and Language Processing (3rd ed. draft)
Dan Jurafsky and James H. Martin : https://web.stanford.edu/~jurafsky/slp3/

Series of Jupyter Notebooks with step-by-step introduction to data science and machine learning

Code : https://github.com/rasbt/python-machine-learning-book-2nd-edition

Computer Vision dataset search

visualdata.io is a great resource for exploring computer vision datasets : https://www.visualdata.io/

Hamiltonian Descent Methods

https://arxiv.org/abs/1809.05042 @ArtificialIntelligenceArticles

ICLR 2019 submission is closed and papers are now available to view

Nearly 1600 submissions received: https://openreview.net/group?id=ICLR.cc%2F2019%2FConference

#iclr2019

Some early keyword analysis and topic modeling:
https://colab.research.google.com/drive/1jG5ilLQUvxvZ-HB60ovc4Ve_UK5ICoFT

Rules of Machine Learning: Best Practices for ML Engineering

By Martin Zinkevich: https://martin.zinkevich.org/rules_of_ml/rules_of_ml.pdf

TherML: The Thermodynamics of Machine Learning

Anonymous: https://openreview.net/forum?id=HJeQToAqKQ&noteId=HJeQToAqKQ @ArtificialIntelligenceArticles

Understanding & Generalizing AlphaGo Zero #ICLR2019

Anonymous: https://openreview.net/forum?id=rkxtl3C5YX

Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks [106pp]

Reviews recent literature in a comprehensive way, and provides an in-depth view of recent advances, current challenges, problem extensions and datasets.

https://arxiv.org/abs/1809.03193 @ArtificialIntelligenceArticles

RTX 2080 Ti Deep Learning Benchmarks
https://lambdalabs.com/blog/2080-ti-deep-learning-benchmarks/

How to train your MAML

By Anonymous: https://openreview.net/forum?id=HJGven05Y7

'TL;DR: MAML is great, but it has many problems, we solve many of those problems and as a result we learn most hyper parameters end to end, speed-up training and inference and set a new SOTA in few-shot learning'

#metalearning #deeplearning #fewshotlearning

"Large scale GAN training for high fidelity natural image synthesis":

Paper: https://openreview.net/pdf?id=B1xsqj09Fm

Samples:https://drive.google.com/drive/folders/1lWC6XEPD0LT5KUnPXeve_kWeY-FxH002

On the Turing Completeness of Modern Neural Network Architectures

By Anonymous: https://openreview.net/forum?id=HyGBdo0qFm @ArtificialIntelligenceArticles

An Introduction to Probabilistic Programming

By Jan-Willem van de Meent, Brooks Paige, Hongseok Yang, Frank Wood: https://arxiv.org/abs/1809.10756 @ArtificialIntelligenceArticles

Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions https://openreview.net/forum?id=r1eEG20qKQ

Manipulating Attributes of Natural Scenes via Hallucination

https://web.cs.hacettepe.edu.tr/~karacan/projects/attribute_hallucination/ @ArtificialIntelligenceArticles

A Review of the Recent History of Natural Language Processing

By Sebastian Ruder: https://blog.aylien.com/a-review-of-the-recent-history-of-natural-language-processing/

Why Momentum Really Works

By Gabriel Goh: https://distill.pub/2017/momentum/

#artificialintelligence #deeplearning #machinelearning