New interesting paper in Super Resolution area https://arxiv.org/abs/1812.04240
arXiv.org
Unsupervised Degradation Learning for Single Image Super-Resolution
Deep Convolution Neural Networks (CNN) have achieved significant performance
on single image super-resolution (SR) recently. However, existing CNN-based
methods use artificially synthetic...
on single image super-resolution (SR) recently. However, existing CNN-based
methods use artificially synthetic...
Collection of MIT courses about Machine Learning
https://deeplearning.mit.edu/
https://deeplearning.mit.edu/
Lex Fridman | MIT Lectures
Lectures on Deep Learning, Robotics, and AI | Lex Fridman | MIT
Lectures on AI given by Lex Fridman and others at MIT.
Tough stuff for real learners - Indian Driving Dataset
https://idd.insaan.iiit.ac.in/
https://idd.insaan.iiit.ac.in/
Organic computers may be our future https://phys.org/news/2018-12-amoeba-approximate-solutions-np-hard-problem.html
phys.org
Amoeba finds approximate solutions to NP-hard problem in linear time
Researchers have demonstrated that an amoeba—a single-celled organism consisting mostly of gelatinous protoplasm—has unique computing abilities that may one day offer a competitive alternative to ...
Interesting way of learning AI by yelling at it https://youtu.be/pc_k-sgUYmY
YouTube
DeepMind’s Take on How To Create a Benign AI
The paper "Scalable agent alignment via reward modeling: a research direction" is available here:
1. https://arxiv.org/abs/1811.07871
2. https://medium.com/@deepmindsafetyresearch/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84
Pick up cool perks…
1. https://arxiv.org/abs/1811.07871
2. https://medium.com/@deepmindsafetyresearch/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84
Pick up cool perks…
Free dataset for cardio rhythm classification
https://irhythm.github.io/cardiol_test_set/
https://irhythm.github.io/cardiol_test_set/
2.3 Billion accounts was hacked (773M unique)
https://www.troyhunt.com/the-773-million-record-collection-1-data-reach/
https://www.troyhunt.com/the-773-million-record-collection-1-data-reach/
Troy Hunt
The 773 Million Record "Collection #1" Data Breach
Many people will land on this page after learning that their email address has appeared in a data breach I've called "Collection #1". Most of them won't have a tech background or be familiar with the concept of credential stuffing so I'm going to write this…
New interesting research from Facebook about simulating focus effect with DNN
https://research.fb.com/publications/deepfocus-siggraph-asia-2018/
https://research.fb.com/publications/deepfocus-siggraph-asia-2018/
Facebook Research
DeepFocus: Learned Image Synthesis for Computational Displays - Facebook Research
In this paper, we introduce DeepFocus, a generic, end-to-end convolutional neural network designed to efficiently solve the full range of computational tasks for accommodation-supporting HMDs. This network is demonstrated to accurately synthesize defocus…
Retail Product Images Checkout Dataset -https://www.kaggle.com/diyer22/retail-product-checkout-dataset
Kaggle
Retail Product Checkout Dataset
A Large-Scale Retail Product Checkout Dataset
Good course from Stanford "Human behavior biology"
https://tjournal.ru/science/84155-vse-25-lekciy-stenfordskogo-kursa-professora-roberta-sapolski-biologiya-povedeniya-cheloveka (russian)
https://tjournal.ru/science/84155-vse-25-lekciy-stenfordskogo-kursa-professora-roberta-sapolski-biologiya-povedeniya-cheloveka (russian)
TJ
Все 25 лекций Стэнфордского курса профессора Роберта Сапольски «Биология поведения человека» — Наука на TJ
Сексуальное поведение, генетика, шизофрения и многое другое в 25 лекциях курса профессора Роберта Сапольски «Биология поведения человека» на русском языке!
Good Kaggle competition that i recommend for everyone https://www.kaggle.com/c/dont-overfit-ii/data
Kaggle
Don't Overfit! II
A Fistful of Samples
Interesting paper for game developers. it can be used to bug fix games just by watching user gameplay, or for example make them harder/simpler without breaking balance.
https://www.cc.gatech.edu/~riedl/pubs/ijcai17.pdf
https://www.cc.gatech.edu/~riedl/pubs/ijcai17.pdf
ML helping not only with sales or finding cats/cars, it also useful in other areas of science
https://phys.org/news/2019-02-machine-reveals-hidden-turtle-pattern.html
https://phys.org/news/2019-02-machine-reveals-hidden-turtle-pattern.html
phys.org
Machine learning reveals hidden turtle pattern in quantum fireworks
Two years ago, physicists at the University of Chicago were greeted with fireworks—atoms shooting out in jets—when they discovered a new form of quantum behavior. But the patterns underlying the bright ...
Guys from IBM just showed their new creation - Project Debater. The AI system that can debate with humans in realtime, with using global information and based on facts and principles that it learned. Its really big step in the way of fully autonomous systems.
https://youtu.be/m3u-1yttrVw
https://youtu.be/m3u-1yttrVw
YouTube
LIVE DEBATE – IBM Project Debater
At Intelligence Squared U.S., we’ve debated AI before – the risks, the rewards, and whether it can change the world – but for the first time, we’re debating with AI.
In partnership with IBM, Intelligence Squared U.S. is hosting a unique debate between a…
In partnership with IBM, Intelligence Squared U.S. is hosting a unique debate between a…
Fresh topic about language modeling from OpenAI, that you should read.
https://blog.openai.com/better-language-models
https://blog.openai.com/better-language-models
Another good thing that you should read - BERT
https://github.com/google-research/bert
https://github.com/google-research/bert
GitHub
GitHub - google-research/bert: TensorFlow code and pre-trained models for BERT
TensorFlow code and pre-trained models for BERT. Contribute to google-research/bert development by creating an account on GitHub.
Old thing but still valuable - Multi-Head Attention https://mlexplained.com/2017/12/29/attention-is-all-you-need-explained/
How to understand rats language
https://www.youtube.com/watch?v=25LYVxTUZhM
https://www.youtube.com/watch?v=25LYVxTUZhM
YouTube
This algorithm decodes rat squeaks and could revolutionize animal research
Rats are social and chatty critters, but most of their chatter is above the frequency that human ears can hear. If researchers could listen to what rats are “saying,” it could change countless experiments. This week, we try our hand at recording ultrasonic…
Interesting paper on tone mapping, decolorization and downscaling. thanks 2minutespapers to came out with it.
https://arxiv.org/abs/1707.09482
https://arxiv.org/abs/1707.09482
arXiv.org
Deep Feature Consistent Deep Image Transformations: Downscaling,...
Building on crucial insights into the determining factors of the visual
integrity of an image and the property of deep convolutional neural network
(CNN), we have developed the Deep Feature...
integrity of an image and the property of deep convolutional neural network
(CNN), we have developed the Deep Feature...