MLST Discord! https://discord.gg/aNPkGUQtc5
Patreon: https://www.patreon.com/mlst
YT: https://youtu.be/snUf_LIfQII
We had a discussion with Dr. Walid Saba about whether or not MLP neural networks can extrapolate outside of the training support, and what it means to extrapolate in a vector space. Then we discussed the concept of vagueness in cognitive science, for example, what does it mean to be "rich" or what is a "pile of sand"? Finally we discussed behaviourism and the reward is enough hypothesis.
References:
A Spline Theory of Deep Networks [Balestriero]
https://proceedings.mlr.press/v80/balestriero18b/balestriero18b.pdf
The animation we showed of the spline theory was created by Ahmed Imtiaz Humayun (https://twitter.com/imtiazprio) and we will be showing an interview with Imtiaz and Randall very soon!
[00:00:00] Intro
[00:00:58] Interpolation vs Extrapolation
[00:24:38] Type 1 Type 2 generalisation and compositionality / Fodor / Systematicity
[00:32:18] Keith's brain teaser
[00:36:53] Neural turing machines / discrete vs continuous / learnability

#101 DR. WALID SABA - Extrapolation, Compositionality and Learnability

Welcome! We engage in fascinating discussions with pre-eminent figures in the AI field. Our flagship show covers current affairs in AI, cognitive science, neuroscience and philosophy of mind with in-depth analysis. Our approach is unrivalled in terms of scope and rigour – we believe in intellectual diversity in AI, and we touch on all of the main ideas in the field with the hype surgically removed. MLST is run by Tim Scarfe, Ph.D (https://www.linkedin.com/in/ecsquizor/) and features regular appearances from MIT Doctor of Philosophy Keith Duggar (https://www.linkedin.com/in/dr-keith-duggar/).

Technology

Tech News

Podcasting

Gadgets

Software How-To

Connor is the CEO of Conjecture and one of the most famous names in the AI alignment movement. This is the "behind the scenes footage" and bonus Patreon interviews from the day of the Beff Jezos debate, including an interview with Daniel Clothiaux. It's a great insight into Connor's philosophy. At the end there is an unreleased additional interview with Beff.


Support MLST:
Please support us on Patreon. We are entirely funded from Patreon donations right now. Patreon supports get private discord access, biweekly calls, very early-access + exclusive content and lots more. 
https://patreon.com/mlst
Donate: https://www.paypal.com/donate/?hosted_button_id=K2TYRVPBGXVNA
If you would like to sponsor us, so we can tell your story - reach out on mlstreettalk at gmail


Topics:
Externalized cognition and the role of society and culture in human intelligence
The potential for AI systems to develop agency and autonomy
The future of AGI as a complex mixture of various components
The concept of agency and its relationship to power
The importance of coherence in AI systems
The balance between coherence and variance in exploring potential upsides
The role of dynamic, competent, and incorruptible institutions in handling risks and developing technology
Concerns about AI widening the gap between the haves and have-nots
The concept of equal access to opportunity and maintaining dynamism in the system
Leahy's perspective on life as a process that "rides entropy"
The importance of distinguishing between epistemological, decision-theoretic, and aesthetic aspects of morality (inc ref to Hume's Guillotine)
The concept of continuous agency and the idea that the first AGI will be a messy admixture of various components
The potential for AI systems to become more physically embedded in the future
The challenges of aligning AI systems and the societal impacts of AI technologies like ChatGPT and Bing
The importance of humility in the face of complexity when considering the future of AI and its societal implications


Disclaimer: this video is not an endorsement of e/acc or AGI agential existential risk from us - the hosts of MLST consider both of these views to be quite extreme. We seek diverse views on the channel.


00:00:00 Intro
00:00:56 Connor's Philosophy
00:03:53 Office Skit
00:05:08 Connor on e/acc and Beff
00:07:28 Intro to Daniel's Philosophy
00:08:35 Connor on Entropy, Life, and Morality
00:19:10 Connor on London
00:20:21 Connor Office Interview
00:20:46 Friston Patreon Preview
00:21:48 Why Are We So Dumb?
00:23:52 The Voice of the People, the Voice of God / Populism
00:26:35 Mimetics
00:30:03 Governance
00:33:19 Agency
00:40:25 Daniel Interview - Externalised Cognition, Bing GPT, AGI
00:56:29 Beff + Connor Bonus Patreons Interview

Connor Leahy - e/acc, AGI and the future.

Professor Chris Bishop is a Technical Fellow and Director at Microsoft Research AI4Science, in Cambridge. He is also Honorary Professor of Computer Science at the University of Edinburgh, and a Fellow of Darwin College, Cambridge. In 2004, he was elected Fellow of the Royal Academy of Engineering, in 2007 he was elected Fellow of the Royal Society of Edinburgh, and in 2017 he was elected Fellow of the Royal Society. Chris was a founding member of the UK AI Council, and in 2019 he was appointed to the Prime Minister’s Council for Science and Technology.


At Microsoft Research, Chris oversees a global portfolio of industrial research and development, with a strong focus on machine learning and the natural sciences.
Chris obtained a BA in Physics from Oxford, and a PhD in Theoretical Physics from the University of Edinburgh, with a thesis on quantum field theory. 


Chris's contributions to the field of machine learning have been truly remarkable. He has authored (what is arguably) the original textbook in the field - 'Pattern Recognition and Machine Learning' (PRML) which has served as an essential reference for countless students and researchers around the world, and that was his second textbook after his highly acclaimed first textbook Neural Networks for Pattern Recognition. 


Recently, Chris has co-authored a new book with his son, Hugh, titled 'Deep Learning: Foundations and Concepts.' This book aims to provide a comprehensive understanding of the key ideas and techniques underpinning the rapidly evolving field of deep learning. It covers both the foundational concepts and the latest advances, making it an invaluable resource for newcomers and experienced practitioners alike.


Buy Chris' textbook here:
https://amzn.to/3vvLcCh


More about Prof. Chris Bishop:
https://en.wikipedia.org/wiki/Christopher_Bishop
https://www.microsoft.com/en-us/research/people/cmbishop/


Support MLST:
Please support us on Patreon. We are entirely funded from Patreon donations right now. Patreon supports get private discord access, biweekly calls, early-access + exclusive content and lots more. 
https://patreon.com/mlst
Donate: https://www.paypal.com/donate/?hosted_button_id=K2TYRVPBGXVNA
If you would like to sponsor us, so we can tell your story - reach out on mlstreettalk at gmail


TOC:
00:00:00 - Intro to Chris
00:06:54 - Changing Landscape of AI
00:08:16 - Symbolism
00:09:32 - PRML
00:11:02 - Bayesian Approach
00:14:49 - Are NNs One Model or Many, Special vs General
00:20:04 - Can Language Models Be Creative
00:22:35 - Sparks of AGI
00:25:52 - Creativity Gap in LLMs
00:35:40 - New Deep Learning Book
00:39:01 - Favourite Chapters
00:44:11 - Probability Theory
00:45:42 - AI4Science
00:48:31 - Inductive Priors
00:58:52 - Drug Discovery
01:05:19 - Foundational Bias Models
01:07:46 - How Fundamental Is Our Physics Knowledge?
01:12:05 - Transformers
01:12:59 - Why Does Deep Learning Work?
01:16:59 - Inscrutability of NNs
01:18:01 - Example of Simulator
01:21:09 - Control

Prof. Chris Bishop's NEW Deep Learning Textbook!

Dr. Philip Ball is a freelance science writer. He just wrote a book called "How Life Works", discussing the how the science of Biology has advanced in the last 20 years. We focus on the concept of Agency in particular. 


He trained as a chemist at the University of Oxford, and as a physicist at the University of Bristol. He worked previously at Nature for over 20 years, first as an editor for physical sciences and then as a consultant editor. His writings on science for the popular press have covered topical issues ranging from cosmology to the future of molecular biology.


YT: https://www.youtube.com/watch?v=n6nxUiqiz9I


Transcript link on YT description


Philip is the author of many popular books on science, including H2O: A Biography of Water, Bright Earth: The Invention of Colour, The Music Instinct and Curiosity: How Science Became Interested in Everything. His book Critical Mass won the 2005 Aventis Prize for Science Books, while Serving the Reich was shortlisted for the Royal Society Winton Science Book Prize in 2014.


This is one of Tim's personal favourite MLST shows, so we have designated it a special edition. Enjoy!


Buy Philip's book "How Life Works" here: https://amzn.to/3vSmNqp


Support MLST:
Please support us on Patreon. We are entirely funded from Patreon donations right now. Patreon supports get private discord access, biweekly calls, early-access + exclusive content and lots more. 
https://patreon.com/mlst
Donate: https://www.paypal.com/donate/?hosted...
If you would like to sponsor us, so we can tell your story - reach out on mlstreettalk at gmail

Philip Ball - How Life Works

Dr. Paul Lessard and his collaborators have written a paper on "Categorical Deep Learning and Algebraic Theory of Architectures". They aim to make neural networks more interpretable, composable and amenable to formal reasoning. The key is mathematical abstraction, as exemplified by category theory - using monads to develop a more principled, algebraic approach to structuring neural networks.


We also discussed the limitations of current neural network architectures in terms of their ability to generalise and reason in a human-like way. In particular, the inability of neural networks to do unbounded computation equivalent to a Turing machine. Paul expressed optimism that this is not a fundamental limitation, but an artefact of current architectures and training procedures.


The power of abstraction - allowing us to focus on the essential structure while ignoring extraneous details. This can make certain problems more tractable to reason about. Paul sees category theory as providing a powerful "Lego set" for productively thinking about many practical problems.


Towards the end, Paul gave an accessible introduction to some core concepts in category theory like categories, morphisms, functors, monads etc. We explained how these abstract constructs can capture essential patterns that arise across different domains of mathematics.


Paul is optimistic about the potential of category theory and related mathematical abstractions to put AI and neural networks on a more robust conceptual foundation to enable interpretability and reasoning. However, significant theoretical and engineering challenges remain in realising this vision.


Please support us on Patreon. We are entirely funded from Patreon donations right now. 
https://patreon.com/mlst
If you would like to sponsor us, so we can tell your story - reach out on mlstreettalk at gmail


Links:
Categorical Deep Learning: An Algebraic Theory of Architectures
Bruno Gavranović, Paul Lessard, Andrew Dudzik,
Tamara von Glehn, João G. M. Araújo, Petar Veličković
Paper: https://categoricaldeeplearning.com/


Symbolica:
https://twitter.com/symbolica
https://www.symbolica.ai/


Dr. Paul Lessard (Principal Scientist - Symbolica)
https://www.linkedin.com/in/paul-roy-lessard/


Interviewer: Dr. Tim Scarfe


TOC:
00:00:00 - Intro
00:05:07 - What is the category paper all about
00:07:19 - Composition
00:10:42 - Abstract Algebra
00:23:01 - DSLs for machine learning
00:24:10 - Inscrutibility
00:29:04 - Limitations with current NNs
00:30:41 - Generative code / NNs don't recurse
00:34:34 - NNs are not Turing machines (special edition)
00:53:09 - Abstraction
00:55:11 - Category theory objects
00:58:06 - Cat theory vs number theory
00:59:43 - Data and Code are one in the same
01:08:05 - Syntax and semantics
01:14:32 - Category DL elevator pitch
01:17:05 - Abstraction again
01:20:25 - Lego set for the universe
01:23:04 - Reasoning
01:28:05 - Category theory 101
01:37:42 - Monads
01:45:59 - Where to learn more cat theory

Dr. Paul Lessard - Categorical/Structured Deep Learning

Dr. Minqi Jiang and Dr. Marc Rigter explain an innovative new method to make the intelligence of agents more general-purpose by training them to learn many worlds before their usual goal-directed training, which we call "reinforcement learning". 

Their new paper is called "Reward-free curricula for training robust world models" https://arxiv.org/pdf/2306.09205.pdf

https://twitter.com/MinqiJiang
https://twitter.com/MarcRigter

Interviewer: Dr. Tim Scarfe

Please support us on Patreon, Tim is now doing MLST full-time and taking a massive financial hit. If you love MLST and want this to continue, please show your support! In return you get access to shows very early and private discord and networking. https://patreon.com/mlst

We are also looking for show sponsors, please get in touch if interested mlstreettalk at gmail. 

MLST Discord: https://discord.gg/machine-learning-street-talk-mlst-937356144060530778

#101 DR. WALID SABA - Extrapolation, Compositionality and Learnability

Download our free app to listen on your phone