Gerat paper

https://arxiv.org/abs/1811.10959

Deep Learning is one of the most highly sought after skills in AI. In this course, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more.
https://www.newworldai.com/cs230-deep-learning-stanford-engineering/

Speed-up the Python code by thousands of times using Cython
https://towardsdatascience.com/boosting-python-noscripts-with-cython-applied-on-raspberry-pi-5ea191292e68

Efficient Transformers: A Survey
Tay et al.: https://arxiv.org/abs/2009.06732
#Transformer #DeepLearning #ArtificialIntelligence

Nguyen et al., Super-Human Performance in Online Low-latency Recognition of Conversational Speech. arXiv:2010.03449 [cs.CV]. arxiv.org/abs/2010.03449

Fourier Neural Operator for Parametric Partial Differential Equations

https://arxiv.org/abs/2010.08895

Dive into Deep Learning with this machine learning course taught by industry veterans.

You'll learn about Random Forests, Gradient Descent, Recurrent Neural Networks, and other key coding concepts. All you need to get started with this course is some Python knowledge and a little high school math. And if you need to brush up on those, freeCodeCamp has you covered. (15 hour YouTube course):

#deeplearning

https://www.freecodecamp.org/news/learn-deep-learning-from-the-president-of-kaggle/

Interested in Learning for Safety-Critical Control?

Check talk at the "Physics ∩ ML" Seminar
http://www.physicsmeetsml.org/

Title: Learning for Safety-Critical Control in Dynamical Systems

Abstract:
This talk describes ongoing research at Caltech on integrating learning into the design of safety-critical controllers for dynamical systems. To achieve control-theoretic guarantees while using powerful function classes such as neural networks, we must carefully integrate conventional control principles with learning into unified frameworks. I will present two paradigms: integration in dynamics modeling and in policy/controller design. Special emphasis on methods that both admit relevant safety guarantees and are practical to deploy.

Featuring work by Caltech students/postdocs/alumni:
Hoang Le (http://hoangle.info/)
Guanya Shi (http://gshi.me/)
Anqi Liu (https://anqiliu-ai.github.io/)
Richard Cheng (https://rcheng805.github.io/)
Jialin Song (https://jialin-song.github.

Microsoft Introduces Lobe: A Free Machine Learning Application That Allows You To Create AI Models Without Coding
https://www.marktechpost.com/2020/10/28/microsoft-introduces-lobe-a-free-machine-learning-application-that-allows-you-to-create-ai-models-without-coding/
GitHub: https://github.com/lobe

paper and code

A proposed a novel AI framework to conduct real-time multi-speaker recognition without any prior registration or pre-training by learning the speaker identification on the fly. Considering the practical problem of online learning with episodically revealed rewards and introduced a solution based on semi-supervised and self-supervised learning methods in a web- based application
INTERSPEECH 2020 - "VoiceID on the fly: A Speaker Recognition System that Learns from Scratch"
https://www.youtube.com/watch?v=QqLnFS5_rCs
code https://github.com/doerlbh/MiniVox
paper https://arxiv.org/pdf/2006.04376.pdf
demo https://www.baihan.nyc/viz/VoiceID/

50 Years at CMU

The Inaugural Raj Reddy Artificial Intelligence Lecture

Join the School of Computer Science as we mark the 50th anniversary of Raj Reddy's arrival at Carnegie Mellon University with the inaugural Raj Reddy Artificial Intelligence Lecture. During this landmark event, you'll hear from 2018 Turing Award winners Yoshua Bengio, Geoffrey Hinton and Yann LeCun. Former Executive Vice President of Artificial Intelligence and Research at Microsoft Harry Shum, CMU President Farnam Jahanian, and SCS Dean Martial Hebert will also offer remark.


https://www.cs.cmu.edu/events/raj-reddy-50

AI pioneer Geoff Hinton: “Deep learning is going to be able to do everything”



"I do believe deep learning is going to be able to do everything, but I do think there’s going to have to be quite a few conceptual breakthroughs. For example, in 2017 Ashish Vaswani et al. introduced transformers, which derive really good vectors representing word meanings. It was a conceptual breakthrough. It’s now used in almost all the very best natural-language processing. We’re going to need a bunch more breakthroughs like that."

https://www.technologyreview.com/2020/11/03/1011616/ai-godfather-geoffrey-hinton-deep-learning-will-do-everything/

Sr. Machine Learning Researcher

Lawrence Livermore National Laboratory, #United #States

http://careers-llnl.ttcportals.com/jobs/5806771-sr-machine-learning-researcher