The Consciousness Prior
Yoshua Bengio : https://arxiv.org/abs/1709.08568
#MachineLearning #DeepLearning #ArtificialIntelligence

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
Yu et al.: https://arxiv.org/abs/1910.10897
#MachineLearning #ArtificialIntelligence #Robotics

Learning to Smell: Using Deep Learning to Predict the Olfactory Properties of Molecules
By Alexander B Wiltschko : https://ai.googleblog.com/2019/10/learning-to-smell-using-deep-learning.html
#DeepLearning #Olfactory #Molecules

Check out our new paper with Fei Deng and Zhuo Zhi on "Generative Hierarchical Modeling of Parts, Objects, and Scenes" https://arxiv.org/pdf/1910.09119.pdf

We learn compositional and interpretable probabilistic scene graphs from images in an unsupervised way via generation

"The most important book I have read in quite some time" (Daniel Kahneman); "A must-read" (Max Tegmark); "The book we've all been waiting for" (Sam Harris)

A leading artificial intelligence researcher lays out a new approach to AI that will enable us to coexist successfully with increasingly intelligent machines

Longlisted for the 2019 Financial Times/McKinsey Business Book of the Year Award
@ArtificialIntelligenceArticles

In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is seen as inevitable and its outcome all too predictable.

In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage.
@ArtificialIntelligenceArticles

If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial.
@ArtificialIntelligenceArticles
In a 2014 editorial co-authored with Stephen Hawking, Russell wrote, "Success in creating AI would be the biggest event in human history. Unfortunately, it might also be the last." Solving the problem of control over AI is not just possible; it is the key that unlocks a future of unlimited promise.
JOIN
@ArtificialIntelligenceArticles

Human Compatible: Artificial Intelligence and the Problem of Control By Stuart Russell epub @ArtificialIntelligenceArticles

Deep Learning & Cognition - A Keynote from Yoshua Bengio
https://blog.re-work.co/deep-learning-and-cognition-a-keynote-from-yoshua-bengio/

[video] " Visipedia: Combining data, machines and experts to distill knowledge"
Pietro Perona, Caltech + AWS
Part of Brains, Minds and Machines Summer Course 2019
https://cbmm.mit.edu/video/visipedia-combining-data-machines-and-experts-distill-knowledge

The Causal Inference book
Miguel A. Hernan and James M. Robins : https://cdn1.sph.harvard.edu/wp-content/uploads/sites/1268/2019/10/ci_hernanrobins_23oct19.pdf
#CausalInference

Bengio is a great researcher.
https://www.bbc.com/news/technology-50166357

Google AI Blog: Learning to Smell: Using Deep Learning to Predict the Olfactory Properties of Molecules
https://ai.googleblog.com/2019/10/learning-to-smell-using-deep-learning.html?m=1

RTFM: Generalising to Novel Environment Dynamics via Reading
Zhong et al.: https://arxiv.org/abs/1910.08210
#ArtificialIntelligence #MachineLearning #ReinforcementLearning

Open discussion of differing world views is essential for progress. Always eager to have my ideas challenged.

I invite ⁦ geoffrey hinton⁩ to help raise level of discussion via public conversation letterwiki

RT if you would like to see this happen

https://letter.wiki/conversations

High-Quality Self-Supervised Deep Image Denoising
Laine et al.: https://arxiv.org/abs/1901.10277
Code : https://github.com/NVlabs/selfsupervised-denoising
#SelfSupervisedLearning #DeepLearning #TensorFlow

Submitted to WACV 2020: Turning low-resolution pictures to super high resolution

https://www.profillic.com/paper/arxiv:1910.08761

a fully convolutional multi-stage neural network for 4× super-resolution for face images.

How to start learning AI

Do show calculus

[https://www.youtube.com/watch?v=fYyARMqiaag&list=PLF797E961509B4EB5](https://www.youtube.com/watch?v=fYyARMqiaag&list=PLF797E961509B4EB5)

calculus 1,2,3

ICYMI from BMVC 2019: human motion transfer - generation of a video
https://www.profillic.com/paper/arxiv:1910.09139
(Their GAN-based architecture, DwNet, leverages dense intermediate pose-guided representation and refinement process to warp the required subject appearance, in the form of the texture, from a source image into a desired pose.)

Bayesian Deep Learning Benchmarks
GitHub, by the Oxford Applied and Theoretical Machine Learning group : https://github.com/OATML/bdl-benchmarks
#Bayesian #DeepLearning #Benchmarks