#junior
Good introduction article about base things
https://towardsdatascience.com/estimators-loss-functions-optimizers-core-of-ml-algorithms-d603f6b0161a
Good introduction article about base things
https://towardsdatascience.com/estimators-loss-functions-optimizers-core-of-ml-algorithms-d603f6b0161a
Medium
Estimators, Loss Functions, Optimizers —Core of ML Algorithms
In order to understand how a machine learning algorithm learns from data to predict an outcome, it is essential to understand the…
Best intro video I've seen for deep reinforcement learning, grounded in example + code.
https://www.youtube.com/watch?v=t1A3NTttvBA
https://www.youtube.com/watch?v=t1A3NTttvBA
YouTube
TensorFlow and deep reinforcement learning, without a PhD (Google I/O '18)
On the forefront of deep learning research is a technique called reinforcement learning, which bridges the gap between academic deep learning problems and ways in which learning occurs in nature in weakly supervised environments. This technique is heavily…
Museum of Dali in Florida, used DeepFake model to create interactive video box with Dali.
"""Next step are movies.
https://youtu.be/BIDaxl4xqJ4
"""Next step are movies.
https://youtu.be/BIDaxl4xqJ4
YouTube
Behind the Scenes: Dalí Lives
Dalí Lives – Art Meets Artificial Intelligence. Exclusively at The Dalí Museum.
The Dalí Museum in St. Petersburg, Florida partnered with Goodby Silverstein & Partners to create a groundbreaking Artificial Intelligence (AI) experience. "Dalí Lives" will…
The Dalí Museum in St. Petersburg, Florida partnered with Goodby Silverstein & Partners to create a groundbreaking Artificial Intelligence (AI) experience. "Dalí Lives" will…
Awesome research from Google RL team. Learning dynamics from video
https://planetrl.github.io
https://planetrl.github.io
PlaNet solves control tasks from pixels by planning in latent space.
Learning Latent Dynamics for Planning from Pixels
Two powerful papers from DeepMind team
https://arxiv.org/abs/1901.11390
https://arxiv.org/abs/1903.00450
https://arxiv.org/abs/1901.11390
https://arxiv.org/abs/1903.00450
arXiv.org
MONet: Unsupervised Scene Decomposition and Representation
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other...
Machine learning speeds modeling of experiments aimed at capturing fusion energy on Earth. The new ML software reduces the time needed to accurately predict the behavior of energetic particles to under 150 microseconds — enabling the calculations to be done online during the experiment
https://research.princeton.edu/news/machine-learning-speeds-modeling-experiments-aimed-capturing-fusion-energy-earth
https://research.princeton.edu/news/machine-learning-speeds-modeling-experiments-aimed-capturing-fusion-energy-earth
Office of the Dean for Research
Machine learning speeds modeling of experiments aimed at capturing fusion energy on Earth
Machine learning (ML), a form of artificial intelligence that recognizes faces, understands language and navigates self-driving cars, can help bring to Earth the clean fusion energy that lights the sun and stars. Researchers at the U.S. Department of Energy’s…
Art + Neural Networsk == Awesome
http://nips4creativity.com/
http://nips4creativity.com/
NIPS Machine Learning Art - Crafting the Future: Where Neural Inspiration Meets Artistic Expression
AI Gallery: Future of Artistic Innovation at NIPS Machine Learning
Dive into the realm of artistic innovation at the AI Gallery, where the NIPS Machine Learning exhibition showcases the forefront of creativity. Explore groundbreaking artworks that blend artificial intelligence with human ingenuity, offering a glimpse into…
Fast AutoAugment is accepted at ICML 2019 AutoML workshop
https://github.com/KakaoBrain/fast-autoaugment
https://github.com/KakaoBrain/fast-autoaugment
GitHub
kakaobrain/fast-autoaugment
Official Implementation of 'Fast AutoAugment' in PyTorch. - kakaobrain/fast-autoaugment
An Easy Guide to Gauge Equivariant Convolutional Networks
Blog by Michael Kissner: https://medium.com/@kayzaks/an-easy-guide-to-gauge-equivariant-convolutional-networks-9366fb600b70
#MachineLearning #DeepLearning #NeuralNetworks #ConvolutionalNetwork
Blog by Michael Kissner: https://medium.com/@kayzaks/an-easy-guide-to-gauge-equivariant-convolutional-networks-9366fb600b70
#MachineLearning #DeepLearning #NeuralNetworks #ConvolutionalNetwork
https://youtu.be/bp9KBrH8H04 Sebastian Thrun Google AI TED Talks Google X Labs Stanford University Udacity
YouTube
Google's driverless car | Sebastian Thrun
http://www.ted.com Sebastian Thrun helped build Google's amazing driverless car, powered by a very personal quest to save lives and reduce traffic accidents. Jawdropping video shows the DARPA Challenge-winning car motoring through busy city traffic with no…
Neural nets are the core machinery that make deep learning so powerful. This radical new design scraps the layers entirely to overcome a major shortcoming in ai .
https://www.technologyreview.com/s/612561/a-radical-new-neural-network-design-could-overcome-big-challenges-in-ai/
https://www.technologyreview.com/s/612561/a-radical-new-neural-network-design-could-overcome-big-challenges-in-ai/
MIT Technology Review
A radical new neural network design could overcome big challenges in AI
David Duvenaud was collaborating on a project involving medical data when he ran up against a major shortcoming in AI. An AI researcher at the University of Toronto, he wanted to build a deep-learning model that would predict a patient’s health over time.…
CoqGym
A Learning Environment for Theorem Proving with the Coq proof assistant
By Princeton Vision & Learning Lab: https://github.com/princeton-vl/CoqGym
#Logic #ComputerScience #ArtificialIntelligence #MachineLearning
A Learning Environment for Theorem Proving with the Coq proof assistant
By Princeton Vision & Learning Lab: https://github.com/princeton-vl/CoqGym
#Logic #ComputerScience #ArtificialIntelligence #MachineLearning
GitHub
GitHub - princeton-vl/CoqGym: A Learning Environment for Theorem Proving with the Coq proof assistant
A Learning Environment for Theorem Proving with the Coq proof assistant - princeton-vl/CoqGym
"HSBC to open 50-person AI lab in Toronto"
https://www.theglobeandmail.com/business/article-hsbc-to-open-50-person-artificial-intelligence-lab-in-toronto/
https://www.theglobeandmail.com/business/article-hsbc-to-open-50-person-artificial-intelligence-lab-in-toronto/
The Globe and Mail
HSBC to open 50-person AI lab in Toronto
Data scientists, engineers and analysts, as well as students, will analyze up to 10 petabytes of data – 10 million gigabytes – in order to help HSBC develop new products and services
Great article on image enhancing (without NN!!!!)
https://sites.google.com/view/handheld-super-res/
https://sites.google.com/view/handheld-super-res/
Google
Handheld Multi-Frame Super-Resolution
We present a multi-frame super-resolution algorithm that supplants the need for demosaicing in a camera pipeline by merging a burst of raw images. In the above figure we show a comparison to a method that merges frames containing the same-color channels…
NLP researchers: help Facebook detect false news.
https://research.fb.com/programs/research-awards/proposals/the-online-safety-benchmark-request-for-proposals/
https://research.fb.com/programs/research-awards/proposals/the-online-safety-benchmark-request-for-proposals/
Facebook Research
The Online Safety Benchmark request for proposals - Facebook Research
The reduction of fake and misleading content on Facebook is mostly driven by the state-of-the-art text and visual recognition systems, including Machine Translation, Automatic Speech and Character Recognition, and Image and Text Categorization. However, we…
Google researchers developed a way to peer inside the minds of deep-learning systems, and the results are delightfully weird.
https://www.technologyreview.com/f/610439/making-sense-of-neural-networks-febrile-dreams/
https://www.technologyreview.com/f/610439/making-sense-of-neural-networks-febrile-dreams/
MIT Technology Review
A new tool helps us understand what an AI is actually thinking
Google researchers developed a way to peer inside the minds of deep-learning systems, and the results are delightfully weird.What they did: The team built a tool that combines several techniques to provide people with a clearer idea of how neural networks…
Turning cortical activity into speech using deep learning.
Pretty cool.
Some ways to go but still pretty cool.
Is the speed of our speech limited by the mechanical constraints of our articulatory apparatus, or is it limited by the speed of our speech-generating cortex?
If it is the former, people with speech-production implants may, one day, be able to speak faster than non-equipped people.
https://www.sciencemag.org/news/2019/01/artificial-intelligence-turns-brain-activity-speech
Pretty cool.
Some ways to go but still pretty cool.
Is the speed of our speech limited by the mechanical constraints of our articulatory apparatus, or is it limited by the speed of our speech-generating cortex?
If it is the former, people with speech-production implants may, one day, be able to speak faster than non-equipped people.
https://www.sciencemag.org/news/2019/01/artificial-intelligence-turns-brain-activity-speech
Science
Artificial intelligence turns brain activity into speech
Fed data from invasive brain recordings, algorithms reconstruct heard and spoken sounds
A triple interview of Geoff, Yoshua and me in the June issue of Communication of the ACM.
https://cacm.acm.org/magazines/2019/6/236987-reaching-new-heights-with-artificial-neural-networks/fulltext
https://cacm.acm.org/magazines/2019/6/236987-reaching-new-heights-with-artificial-neural-networks/fulltext
cacm.acm.org
Reaching New Heights with Artificial Neural Networks
ACM A.M. Turing Award recipients Yoshua Bengio, Geoffrey Hinton, and Yann LeCun on the promise of neural networks, the need for new paradigms, and the concept of making technology accessible to all.
A Guide for Making Black Box Models Explainable
By Christoph Molnar: https://christophm.github.io/interpretable-ml-book/ …
#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks
By Christoph Molnar: https://christophm.github.io/interpretable-ml-book/ …
#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks
christophm.github.io
Interpretable Machine Learning