​​Photo to anime portrait

U-GAT-IT — Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation.

Link: https://github.com/taki0112/UGATIT

#Tensorflow #GAN #CV #DL #anime

​​Unified rational protein engineering with sequence-only deep representation learning

UniRep predicts amino-acid sequences that form stable bonds. In industry, that’s vital for determining the production yields, reaction rates, and shelf life of protein-based products.

Link: https://www.biorxiv.org/content/10.1101/589333v1.full

#biolearning #rnn #Harvard #sequence #protein

A Guide for Making Black Box Models Explainable.

One of the biggest challenges is to make ML models interpretable (explainable to human, preferably, non-expert). It matters not only in terms of credit scoring, to exclude possibility of racism or any other bias or news promotion and display (Cambridge Analytica case), but even in terms of debug and further progress in model training.


Link: https://christophm.github.io/interpretable-ml-book/

#guide #interpretablelearning #IL

🔥 New Releases: PyTorch 1.2, torchtext 0.4, torchaudio 0.3, and torchvision 0.4

https://pytorch.org/blog/pytorch-1.2-and-domain-api-release/

https://github.com/pytorch/pytorch/releases

​​Simple real time visualisation of the execution of a #python program: https://github.com/alexmojaki/heartrate

Community Day @ MLSS 2019

MLSS Community Day is a free one-day event for everyone interested in Machine Learning.

Speakers from premier institutions in Machine Learning such as the University of Oxford, University College London, Max Planck Institute as well as renowned companies will cover the latest advances in applications for healthcare, telecommunications, NLP, finance, and quantum computing.

When & Where: August 31, Skoltech, Moscow
Link: https://mlss2019.skoltech.ru/community-day

#MLSS #MLSS2019 #Skolkovo

DeepMind's Behaviour Suite for Reinforcement Learning

DeepMind released Behaviour Suite for Reinforcement Learning, or ‘bsuite’ – a collection of carefully-designed experiments that investigate core capabilities of RL agents.

bsuite was built to do two things:

1. Offer clear, informative, and scalable experiments that capture key issues in RL
2. Study agent behaviour through performance on shared benchmarks

GitHub: https://github.com/deepmind/bsuite
Paper: https://arxiv.org/abs/1908.03568v1
Google colab: https://colab.research.google.com/drive/1rU20zJ281sZuMD1DHbsODFr1DbASL0RH

#RL #DeepMind #Bsuite

Neural Text d̶e̶Generation with Unlikelihood Training

Introducing a new objective, unlikelihood training, which forces unlikely generations to be assigned lower probability by the model, which improves overall quality of generated text.

Link: https://arxiv.org/pdf/1908.04319.pdf

#NLU #NLP #textgeneration

ODS breakfast in Paris! See you this Saturday at 10:30 at Malongo Café, 50 Rue Saint-André des Arts.

​​🥇Parameter optimization in neural networks.

Play with three interactive visualizations and develop your intuition for optimizing model parameters.

Link: https://www.deeplearning.ai/ai-notes/optimization/

#interactive #demo #optimization #parameteroptimization #novice #entrylevel #beginner #goldcontent #nn #neuralnetwork

The HSIC Bottleneck: Deep Learning without Back-Propagation

An alternative to conventional backpropagation, that has a number of distinct advantages.

Link: https://arxiv.org/abs/1908.01580

#nn #backpropagation #DL #theory

If you happen to be in Moscow in the next couple of weeks, we invite you to take part in Moscow Data Science Major on August 31st at Mail.ru Group office!

It’s like OpenDataScience’s Data Fest, but a mini version (in terms of duration, not content density). It’s like 1st of October, but 31st of August.

MDSM gather all researchers, engineers and developers around Data Science and Machine Learning:
- Top speakers and talks, zero bullshit
- Lots of new insights, skills and know-hows
- Best networking with the community

Link: https://datafest.ru/major/
Registration link: https://corp.mail.ru/ru/press/events/mdsm_aug19/

GPT-2: 6-Month Follow-Up

#OpenAI released the 774 million parameter #GPT2 language model.

Link: https://openai.com/blog/gpt-2-6-month-follow-up/

#NLU #NLP

Applying machine learning optimization methods to the production of a quantum gas

#DeepMind developed machine learning techniques to optimise the production of a Bose-Einstein condensate, a quantum-mechanical state of matter that can be used to test predictions of theories of many-body physics.

ArXiV: https://arxiv.org/abs/1908.08495

#Physics #DL #BEC

​​Testing Robustness Against Unforeseen Adversaries

OpenAI developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during training. The method yields a new metric, #UAR (Unforeseen Attack Robustness), which evaluates the robustness of a single model against an unanticipated attack, and highlights the need to measure performance across a more diverse range of unforeseen attacks.

Link: https://openai.com/blog/testing-robustness/
ArXiV: https://arxiv.org/abs/1908.08016
Code: https://github.com/ddkang/advex-uar

#GAN #Adversarial #OpenAI

OpenGPT-2: We Replicated GPT-2 Because You Can Too

Article about replication of famous #GPT2. This replication project trained a 1.5B parameter «OpenGPT-2» model on OpenWebTextCorpus, a 38GB dataset similar to the original, and showed comparable results to original GPT-2 on various benchmarks.

Link: https://medium.com/@vanya_cohen/opengpt-2-we-replicated-gpt-2-because-you-can-too-45e34e6d36dc
Google colab: https://colab.research.google.com/drive/1esbpDOorf7DQJV8GXWON24c-EQrSKOit
OpenWebCorpus: https://skylion007.github.io/OpenWebTextCorpus/

#NLU #NLP

Open-sourcing hyperparameter autotuning for fastText

Facebook AI researchers are releasing a new feature for the fastText library which provides hyper-parameter autotuning for more efficient text classifiers.

Link: https://ai.facebook.com/blog/fasttext-blog-post-open-source-in-brief/

#FacebookAI #Facebook #FastText #NLU #NLP

​​The infinite gift

is an interesting object where the side of the nth box is 1/√n. As n→+∞, the gift has infinite surface area and length but finite volume!

​​Exploring Weight Agnostic Neural Networks

Exploration of agents that can already perform well in their environment without the need to learn weight parameters.

Link: https://ai.googleblog.com
Code: https://github.com/google/brain-tokyo-workshop/tree/master/WANNRelease