During the pandemic DeepMind has been publishing a series of short posts on LinkedIn (tagged as #AtHomeWithAI) with a collection of resources that some of their staff find interesting. In a time where there is a lot of noise surrounding Machine Learning finding really good resources to learn from is not trivial.
This collection ranges from RL, DL to Operational Research, Bias in ML, Probabilistic Models, etc. I don't think I have ever seen a more curated and pure useful collection of resources ever. Unsurprisingly, DeepMind people know what they are talking about. I have been collecting their posts and since the series ended a few days ago I thought I should share them. Here it is.
For those interested in expanding their knowledge of AI during this period, we thought it might be helpful to ask our researchers what they consider to be the most impactful and insightful resources available to use #AtHomeWithAI.
First up is Feryal Behbahani, research scientist. She recommends the following:
- Stanford’s Emma Brunskill on RL https://bit.ly/3eAArB9
- Lectures, slides and Colabs from khipu.ai: https://bit.ly/2KkDX4U
- Stanford’s Chelsea Finn on multi-task and meta-learning methods: https://bit.ly/3bowUUl
- Spinning up in Deep RL from OpenAI: https://bit.ly/2KfQbvw
- Oxford’s ML course taught by DeepMind research scientist Nando de Freitas: https://bit.ly/3fj6YvU
- The Brain Inspired podcast - where AI meets neuroscience: https://bit.ly/2ysvGco
- Lectures from the late David MacKay: https://bit.ly/2xJ7NgC
Our latest set of #AtHomeWithAI recommendations come from Keren Gu-Lemberg, research engineer at DeepMind. From videos to games, her suggestions are great for anyone looking for a more interactive and hands-on approach to learning.
- Introduction to machine learning: https://bit.ly/2VSb4lJ
- Introduction to deep learning: https://bit.ly/2Vx5ZQI
- Project Euler: https://bit.ly/3bxBmAj
- Full stack deep learning bootcamp: https://bit.ly/3bztYV9
We’re back with the latest set of #AtHomeWithAI recommendations - this time from research scientist Adam Marblestone! He suggests:
- Computational Models of the Neocortex: https://lnkd.in/eBRB43T
- Key ideas in linear algebra: https://bit.ly/3buHbi6
- An introduction to probabilistic graphical models: https://bit.ly/2xSxVWe
- Nonlinear dynamics and chaos lecture series: https://bit.ly/3eFoied
- A course on the Human Intelligence Enterprise: https://bit.ly/3cRZePW
We’re back with more suggestions from our researchers for ways to expand your knowledge of AI. Today’s #AtHomeWithAI recommendations are from research scientist Kimberly Stachenfeld!
- The Scientist in the Crib [longer listen]: https://adbl.co/2Wwp5pE
- Brains, minds & machines summer course: https://bit.ly/351M6V5
- Computational systems neuroscience series: https://bit.ly/2VzCez2
- Theoretical neuroscience [longer read]: https://bit.ly/2xLt2yv
- The appeal of parallel distributed processing [longer read]: https://lnkd.in/d-Uiqas
Continuing with the sharing of insightful resources for those at home, up next is software engineer Julian Schrittwieser, one of the team behind #AlphaZero.
His #AtHomeWithAI recommendations include:
- JAX-based neural network library: https://bit.ly/2zBIkpR
- Neural networks and deep learning [longer read]: https://bit.ly/3ePYa06
- Deep learning book [longer read]: https://bit.ly/351qMzb
- A dive into deep learning: http://d2l.ai/
- Video lectures from @UCL professor, co-creator of #AlphaZero, #AlphaStar & recent ACM Prize winner, David Silver: https://bit.ly/2Kt8w8l
Looking to learn more about AI? Our researchers are continuing to share their #AtHomeWithAI recommendations. Today’s choices come from William Isaac, a senior research scientist who specialises in ethics, bias and fairness. He suggests:
- The free fairness and machine learning book [longer read]: https://bit.ly/350VoAO
- Arvind Narayanan’s “21 definitions of fairness and their politics”: https://bit.ly/2S21KuE
- The trouble with bias - a talk by Kate Crawford: https://bit.ly/3aGFBZm
- A discussion of fairness in machine learning with Solon Barocas and Moritz Hardt https://bit.ly/2VU49bV
We’re back with more researcher recommendations for ways to expand your knowledge of AI. Today’s suggestions come from Victoria Krakovna, research scientist in AI safety. She recommends:
- Robert Miles YouTube channel: https://bit.ly/3dKwVTB
- Human Compatible: Artificial Intelligence and the Problem of Control: https://bit.ly/2LrH2jY
- The Alignment Newsletter: https://bit.ly/3czfMw1
Looking for a few more favourite resources from the team? Today’s #AtHomeWithAI picks are from research scientist Taylan Cemgil! He recommends:
- 3Blue1Brown YouTube channel: https://bit.ly/362p0OI
- Basics of probabilistic reasoning and modelling: https://bit.ly/3cG99rS
- A Tutorial Introduction to Monte Carlo methods, Markov Chain Monte Carlo and Particle Filtering: https://bit.ly/3cAQ8XG
- Ramon van Handel's "Probability in High Dimension”: https://bit.ly/2yOuyjT
- Open-source visualisation library: https://bit.ly/2y977RY
We’re back with more #AtHomeWithAI researcher recommendations. Next up is research scientist Silvia Chiappa with suggestions for resources to learn about causal inference. She recommends:
- The Book of Why: https://bit.ly/36A2Cwo
- Causal Inference in Statistics: A Primer: https://bit.ly/36xdvza
- The Elements of Causal Inference: https://bit.ly/3gCqowy
- Decision-theoretic foundations for statistical causality: https://bit.ly/2XFjAGR
Up next in our #AtHomeWithAI series is research scientist Jessica Hamrick! See below for her favourite resources:
- Probabilistic Models of Cognition: https://bit.ly/3eM05lN
- Computational cognitive modeling: https://bit.ly/309pvWy
- Nelson Goodman’s “The New Riddle of Induction”: https://bit.ly/2Bv4FGB
- Marr's Vision: Levels of Analysis in Cognitive Science [chapter 1]: https://bit.ly/3cypLkr
We’re back with more researcher recommendations! Today we have suggestions from research scientist Razvan Pascanu. He suggests:
- Lab materials & practicals from the EEML summer school: https://bit.ly/2yYNgoV & https://bit.ly/2LwOD0E
- Lecture slides from EEML: https://bit.ly/2WA5rdw
- Lviv Machine Learning Workshop talk on ML: https://bit.ly/2yRQoTE
- Herbert Jaeger’s tutorial on training recurrent models: https://bit.ly/3bWu2O5
Up next in our #AtHomeWithAI series is research scientist Sebastian Ruder! His recommendations cover the fundamentals of Deep Learning & have a specific focus on natural language processing. He suggests:
- Deep Learning Book: https://bit.ly/351qMzb
- Free code camp curated list: https://bit.ly/3erZEN4
- A Code-First Introduction to Natural Language Processing: https://bit.ly/3esFtP8
- Stanford resources on Natural Language Processing: https://lnkd.in/er9BbTB & https://lnkd.in/eRKm8Dj
- Primer on neural network models: https://bit.ly/3eth9Ni
- Gradient-based optimisation blog: https://bit.ly/2ZI3Fck
- NLP-progress: https://bit.ly/3gvh1i3
We’re back with more #AtHomeWithAI researcher recommendations. Today we have research scientist Patrick Pilarski! He suggests:
- The RL specialisation course: https://bit.ly/2X8G1Uu
- Machine learning: Algorithms in the Real World Specialisation: https://bit.ly/3esZo0E
- WEKA - a free open source machine learning toolset: https://bit.ly/2zCTNpD
Today we have #AtHomeWithAI recommendations from research scientist Dani Yogatama! His suggestions are specifically geared towards those interested in machine learning.
- Mathematics for Machine Learning: https://bit.ly/2MNM4rD
- Francis Bach’s blog: https://bit.ly/3dRE8S2 #AtHomeWithAI
- Standford’s Machine Learning lectures: https://bit.ly/2MKAMED
We’re back with more #AtHomeWithAI researcher recommendations! Today we have research engineer Mihaela Rosca. She recommends:
- The mathematicalmonk on YouTube: https://bit.ly/2Ae3QSx
- Variational Inference: A Review for Statisticians: https://bit.ly/3cQgPH8
- Monte Carlo Gradient Estimation in Machine Learning: https://bit.ly/2MP8rNi
- The Reproducing kernel Hilbert spaces in Machine Learning course: https://bit.ly/3dSY0Ev
Up next in the #AtHomeWithAI series is research scientist Markus Wulfmeier! He suggests the following resources for those looking to learn:
- Stanford’s computer vision course: https://lnkd.in/dYJWDc6
- Neural network tutorials: https://bit.ly/3fnJdlA
- Lilian Weng’s blog: https://bit.ly/3fr2JNY
We’re back with the final round of #AtHomeWithAI researcher recommendations & today we have research engineer Ngân Vũ! She recommends:
- A 2020 vision of Linear Algebra: https://bit.ly/37w2OND
- The Artificial Intelligence podcast: https://bit.ly/3cYwWCp
- Reinforcement Learning: An Introduction: https://bit.ly/3fkalBU
- Machine Learning course (via Coursera): https://bit.ly/2ULHCxZ