Using electrode implants that feed data into computational models known as neural networks, scientists reconstructed words and sentences from brain activity that were, in some cases, intelligible to human listeners.

https://www.sciencemag.org/news/2019/01/artificial-intelligence-turns-brain-activity-speech

@ArtificialIntelligenceArticles

Designing neural networks through Neuroevolution

https://www.nature.com/articles/s42256-018-0006-z

This Tensorflow based Python Library ‘Spleeter’ splits vocals from finished tracks

Github: https://github.com/deezer/spleeter

https://www.marktechpost.com/2019/11/10/this-tensorflow-based-python-library-spleeter-splits-vocals-from-finished-tracks/

Probabilistic Logic Neural Networks for Reasoning
Meng Qu, Jian Tang : https://arxiv.org/abs/1906.08495
#MachineLearning #ArtificialIntelligence #NeuralNetworks

US National Security Commission on Artificial Intelligence

Interim Report for Congress, November 2019

#AI #ArtificialIntelligence #Security #NSCAI

https://www.nationaldefensemagazine.org/-/media/sites/magazine/03_linkedfiles/nscai-interim-report-for-congress.ashx?la=en

My position is very similar to Yoshua's.
Making sequential reasoning compatible with gradient-based learning is one of the challenges of the next decade.
But gradient-based learning applied to networks of parameterized modules (aka "deep learning") is part of the solution.


Gary Marcus likes to cite me when I talk about my current research program which studies the weaknesses of current deep learning systems in order to devise systems stronger in higher-level cognition and greater combinatorial (and systematic) generalization, including handling of causality and reasoning. He disagrees with the view that Yann LeCun, Geoff Hinton and I have expressed that neural nets can indeed be a "universal solvent" for incorporating further cognitive abilities in computers. He prefers to think of deep learning as limited to perception and needing to be combined in a hybrid with symbolic processing. I disagree in a subtle way with this view. I agree that the goals of GOFAI (like the ability to perform sequential reasoning characteristic of system 2 cognition) are important, but I believe that they can be performed while staying in a deep learning framework, albeit one which makes heavy use of attention mechanisms (hence my 'consciousness prior' research program) and the injection of new architectural (e.g. modularity) and training framework (e.g. meta-learning and an agent-based view). What I bet is that a simple hybrid in which the output of the deep net are discretized and then passed to a GOFAI symbolic processing system will not work. Why? Many reasons: (1) you need learning in the system 2 component as well as in the system 1 part, (2) you need to represent uncertainty there as well (3) brute-force search (the main inference tool of symbol-processing systems) does not scale, instead humans use unconscious (system 1) processing to guide the search involved in reasoning, so system 1 and system 2 are very tightly integrated and (4) your brain is a neural net all the way

https://t.iss.one/ArtificialIntelligenceArticles

Optimizing Millions of Hyperparameters by Implicit Differentiation
Lorraine et al.: https://arxiv.org/abs/1911.02590
#ArtificialIntelligence #MachineLearning

Seeing What a GAN Cannot Generate
https://ganseeing.csail.mit.edu/

Free linear Algebra textbook with solutions https://joshua.smcvt.edu/linearalgebra/#current_version

A neural network that transforms a design mock-up into a static website
GitHub by Emil Wallner : https://github.com/emilwallner/Screenshot-to-code
#ArtificialIntelligence #DeepLearning #MachineLearning

Story Realization: Expanding Plot Events into Sentences
Ammanabrolu et al.: https://arxiv.org/abs/1909.03480
#ArtificialIntelligence #DeepLearning #MachineLearning

Knowledge Distillation for Incremental Learning in Semantic Segmentation. https://arxiv.org/abs/1911.03462

AIM 2019 Challenge on Image Demoireing: Methods and Results. https://arxiv.org/abs/1911.03461

Towards Domain Adaptation from Limited Data for Question Answering Using Deep Neural Netw... https://arxiv.org/abs/1911.02655

Worst Cases Policy Gradients
Yichuan Charlie Tang, Jian Zhang, Ruslan Salakhutdinov : https://arxiv.org/abs/1911.03618
#MachineLearning #DeepLearning #ArtificialIntelligence

Teaching a neural network to use a calculator
Blog by Reiichiro Nakano : https://reiinakano.com/2019/11/12/solving-probability.html
#ArtificialIntelligence #DeepLearning #MachineLearning