Building a Powerful DQN in TensorFlow 2.0 (explanation & tutorial)
Sebastian Theiler: https://medium.com/analytics-vidhya/building-a-powerful-dqn-in-tensorflow-2-0-explanation-tutorial-d48ea8f3177a
#ReinforcementLearning #MachineLearning #Python #TensorFlow

Monte Carlo Sampling using Langevin Dynamics
I wrote an article on the basics of Langevin Monte Carlo techniques. Please let me know if you find any errors.

Code: https://github.com/abdulfatir/langevin-monte-carlo
Visualization: https://www.youtube.com/watch?v=cVn0kru3hL8

I hope it's helpful for someone. :)

https://abdulfatir.com/Langevin-Monte-Carlo/

Google’s Dataset Search
"Dataset Search has indexed almost 25 million of these datasets, giving you a single place to search for datasets & find links to where the data is.” — Natasha Noy
https://datasetsearch.research.google.com
#ArtificialIntelligence #Datasets #MachineLearning

"Jack London wrote 1,000 words every day before talking to anybody. He was totally, “Let me alone until I’ve got my thousand words!” Then he would drink or proofread the rest of the day. No, my scheduling principle is to do the thing I hate most on my to-do list. By week’s end, I’m very happy....

A person’s success in life is determined by having a high minimum, not a high maximum. If you can do something really well but there are other things at which you’re failing, the latter will hold you back. But if almost everything you do is up there, then you’ve got a good life. And so I try to learn how to get through things that others find unpleasant."


https://www.quantamagazine.org/computer-scientist-donald-knuth-cant-stop-telling-stories-20200416/

Got data and wonder if there's a formula describing it? There's a new physics-inspired AI Feynman algorithm, published today. It automates what took Kepler 4 years.
v/@tegmark
https://bit.ly/3esOWH3
"A core challenge for both physics and artificial intelligence (AI) is symbolic regression: finding a symbolic expression
that matches data from an unknown function. Although this problem is likely to be NP-hard in principle, functions
of practical interest often exhibit symmetries, separability, compositionality, and other simplifying properties.
In this spirit, we develop a recursive multidimensional symbolic regression algorithm that combines neural network
fitting with a suite of physics-inspired techniques. We apply it to 100 equations from the Feynman Lectures on Physics,
and it discovers all of them, while previous publicly available software cracks only 71; for a more difficult physicsbased test set, we improve the state-of-the-art success rate from 15 to 90%"

A great course on Artificial Intelligence and Data Science from one of the best universities in the world.

Lecture 1 - Welcome | Stanford CS229: Machine Learning (Autumn 2018) https://www.youtube.com/watch?v=jGwO_UgTS7I

Capsule Networks -- A Probabilistic Perspective
Smith et al.: https://arxiv.org/abs/2004.03553
#ArtificialIntelligence #CapsuleNetworks #MachineLearning

Detecto — An object detection library for PyTorch
https://medium.com/pytorch/detecto-build-and-train-object-detection-models-with-pytorch-5f31b68a8109

We recently started to write an article review series on Generative Adversarial Networks focused on Computer Vision applications primarily. As I think that there isn't a complete overview on the field anywhere online ( at least I haven't found anything yet), I thought that it would be very helpful for many to gather the most important papers on a couple of articles, accumulated years of reading and research in a single resource.

You can find the first 2 parts below:

https://theaisummer.com/gan-computer-vision/

https://theaisummer.com/gan-computer-vision-object-generation/

Clustering Time Series Data through Autoencoder-based Deep Learning Models. https://arxiv.org/abs/2004.07296

Papers with Code: A searchable site that links machine learning papers on ArXiv with code on GitHub. They also tag any framework libraries used, along with other info like GitHub stars. I think such a feature would be a nice addition to ArXiv-Sanity. https://paperswithcode.com

Your 100% up-to-date guide to transfer learning & fine-tuning with Keras: https://colab.research.google.com/drive/17vHSAj7no7RMdJ18MJomTf8twqw1suYC

Batch normalization involves many gotchas you need to be aware of.

Top 10 Popular GitHub Repositories to learn about Data Science.
https://towardsdatascience.com/top-10-popular-github-repositories-to-learn-about-data-science-4acc7b99c44

Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective
Luis Lamb et al.: https://arxiv.org/abs/2003.00330
#aidebate #thinkingfastandslow #AAAI2020debate #neurosymbolic #neurosymboliccomputing

NVIDIA and King’s College London Announce MONAI Open Source AI Framework for Healthcare Research

https://blogs.nvidia.com/blog/2020/04/21/monai-open-source-framework-ai-healthcare/?ncid=so-face-62055#cid=ix11_so-face_en-us

The ACM just made its entire archive available for free until June 30.
7 magazines
30+ textbooks
50+ journals
Proceedings from 170+ annual conferences, symposia & workshops
Start your journey here
dl.acm.org
ACM - Association for Computing Machinery

We are excited to host the ICLR 2020 workshop “Tackling Climate Change with Machine Learning” from April 26-30. This workshop will feature talks, panels, and posters on work at the intersection of climate change and machine learning; tutorials on climate change and ML; and plenty of opportunities for digital networking with other participants.

All talks and panels will be live-streamed for free via the workshop website. Registration (via the main ICLR conference) is required to participate actively in Q&As, poster sessions, and the conference messaging app.

More details:

The main workshop on April 26 will feature a full-day program of invited and contributed presentations, as well as panel discussions and breakout sessions. Keynote speakers include:

Stefano Ermon (Stanford University)
Ciira wa Maina (Dedan Kimathi University of Technology)
Georgina Campbell (ClimaCell)
Dan Morris (Microsoft AI for Earth)

From April 27-30, our program will feature deep dives into specific sectors of relevance to climate change, via panels, fireside chats, small-group discussions, and tutorials.

April 27: Energy Day
April 28: Agriculture, Forestry, and Other Land Use (AFOLU) Day
April 29: Climate Science and Adaptation Day
April 30: Cross-cutting Methods Day
Schedule and details: https://www.climatechange.ai/ICLR2020_workshop
Registration: Via the main ICLR conference, at https://iclr.cc
Contact: [email protected]

Organizers:

Priya Donti (CMU), David Rolnick (UPenn), Lynn Kaack (ETH Zürich), Sasha Luccioni (Mila), Kris Sankaran (Mila), Sharon Zhou (Stanford), Moustapha Cisse (Google), Carla Gomes (Cornell), Andrew Ng (Stanford), Yoshua Bengio (Mila)

Priya Lekha Donti, David Rolnick, Sasha Lu, Sharon Zhou, Moustapha Cisse, Andrew Ng, Ciira Maina