AI Trends 2024: Reinforcement Learning in the Age of LLMs with Kamyar Azizzadenesheli - #670
Today we’re joined by Kamyar Azizzadenesheli, a staff researcher at Nvidia, to continue our AI Trends 2024 series. In our conversation, Kamyar updates us on the latest developments in reinforcement learning (RL), and how the RL community is taking advantage of the abstract reasoning abilities of large language models (LLMs). Kamyar shares his insights on how LLMs are pushing RL performance forward in a variety of applications, such as ALOHA, a robot that can learn to fold clothes, and Voyager, an RL agent that uses GPT-4 to outperform prior systems at playing Minecraft. We also explore the progress being made in assessing and addressing the risks of RL-based decision-making in domains such as finance, healthcare, and agriculture. Finally, we discuss the future of deep reinforcement learning, Kamyar’s top predictions for the field, and how greater compute capabilities will be critical in achieving general intelligence.
The complete show notes for this episode can be found at twimlai.com/go/670.
TikTok Gets Ready to Testify, UBS Rescues Credit Suisse, and Guest Dr. Gloria Mark
Kara and Scott discuss another round of Amazon layoffs, former President Trump’s call for protests, and of course, raccoon dogs. Plus, the banking drama continues as banks in the U.S. and Switzerland come together to rescue the weakest among them. Also, TikTok CEO Shou Zi Chew will testify before Congress this week. Friend of Pivot Dr. Gloria Mark explains how technology has impacted our attention spans.
You can find Dr. Gloria Mark at @GloriaMark_PhD on Twitter, and you can buy her book “Attention Span: A Groundbreaking Way to Restore Balance, Happiness, and Productivity” here.
Send us your questions! Call 855-51-PIVOT or go to nymag.com/pivot.
Learn more about your ad choices. Visit podcastchoices.com/adchoices
AI Trends 2023: Natural Language Proc - ChatGPT, GPT-4 and Cutting Edge Research with Sameer Singh - #613
Today we continue our AI Trends 2023 series joined by Sameer Singh, an associate professor in the department of computer science at UC Irvine and fellow at the Allen Institute for Artificial Intelligence (AI2). In our conversation with Sameer, we focus on the latest and greatest advancements and developments in the field of NLP, starting out with one that took the internet by storm just a few short weeks ago, ChatGPT. We also explore top themes like decomposed reasoning, causal modeling in NLP, and the need for “clean” data. We also discuss projects like HuggingFace’s BLOOM, the debacle that was the Galactica demo, the impending intersection of LLMs and search, use cases like Copilot, and of course, we get Sameer’s predictions for what will happen this year in the field.
The complete show notes for this episode can be found at twimlai.com/go/613.
#73 - YASAMAN RAZEGHI & Prof. SAMEER SINGH - NLP benchmarks
Patreon: https://www.patreon.com/mlst
Discord: https://discord.gg/ESrGqhf5CB
YT version: https://youtu.be/RzGaI7vXrkk
This week we speak with Yasaman Razeghi and Prof. Sameer Singh from UC Urvine. Yasaman recently published a paper called Impact of Pretraining Term Frequencies on Few-Shot Reasoning where she demonstrated comprehensively that large language models only perform well on reasoning tasks because they memorise the dataset. For the first time she showed the accuracy was linearly correlated to the occurance rate in the training corpus, something which OpenAI should have done in the first place!
We also speak with Sameer who has been a pioneering force in the area of machine learning interpretability for many years now, he created LIME with Marco Riberio and also had his hands all over the famous Checklist paper and many others.
We also get into the metric obsession in the NLP world and whether metrics are one of the principle reasons why we are failing to make any progress in NLU.
[00:00:00] Impact of Pretraining Term Frequencies on Few-Shot Reasoning
[00:14:59] Metrics
[00:18:55] Definition of reasoning
[00:25:12] Metrics (again)
[00:28:52] On true believers
[00:33:04] Sameers work on model explainability / LIME
[00:36:58] Computational irreducability
[00:41:07] ML DevOps and Checklist
[00:45:58] Future of ML devops
[00:49:34] Thinking about future
Prof. Sameer Singh
https://sameersingh.org/
Yasaman Razeghi
https://yasamanrazeghi.com/
References;
Impact of Pretraining Term Frequencies on Few-Shot Reasoning [Razeghi et al with Singh]
https://arxiv.org/pdf/2202.07206.pdf
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList [Riberio et al with Singh]
https://arxiv.org/pdf/2005.04118.pdf
“Why Should I Trust You?” Explaining the Predictions of Any Classifier (LIME) [Riberio et al with Singh]
https://arxiv.org/abs/1602.04938
Tim interviewing LIME Creator Marco Ribeiro in 2019
https://www.youtube.com/watch?v=6aUU-Ob4a8I
Tim video on LIME/SHAP on his other channel
https://www.youtube.com/watch?v=jhopjN08lTM
Our interview with Christoph Molar
https://www.youtube.com/watch?v=0LIACHcxpHU
Interpretable Machine Learning book @ChristophMolnar
https://christophm.github.io/interpretable-ml-book/
Machine Teaching: A New Paradigm for Building Machine Learning Systems [Simard]
https://arxiv.org/abs/1707.06742
Whimsical notes on machine teaching
https://whimsical.com/machine-teaching-Ntke9EHHSR25yHnsypHnth
Gopher paper (Deepmind)
https://www.deepmind.com/blog/language-modelling-at-scale-gopher-ethical-considerations-and-retrieval
https://arxiv.org/pdf/2112.11446.pdf
EleutherAI
https://www.eleuther.ai/
https://github.com/kingoflolz/mesh-transformer-jax/
https://pile.eleuther.ai/
A Theory of Universal Artificial Intelligence based on Algorithmic Complexity [Hutter]
https://arxiv.org/pdf/cs/0004001.pdf
Trends in Deep Reinforcement Learning with Kamyar Azizzadenesheli - #560
Today we’re joined by Kamyar Azizzadenesheli, an assistant professor at Purdue University, to close out our AI Rewind 2021 series! In this conversation, we focused on all things deep reinforcement learning, starting with a general overview of the direction of the field, and though it might seem to be slowing, thats just a product of the light being shined constantly on the CV and NLP spaces. We dig into themes like the convergence of RL methodology with both robotics and control theory, as well as a few trends that Kamyar sees over the horizon, such as self-supervised learning approaches in RL. We also talk through Kamyar’s predictions for RL in 2022 and beyond. This was a fun conversation, and I encourage you to look through all the great resources that Kamyar shared on the show notes page at twimlai.com/go/560!
Rerun: Working with the Large Hadron Collider
Jonathan is joined by Daniel Whiteson of Daniel and Jorge Explain the Universe. Daniel works in the field of experimental particle physics and conducts research using the LHC.
Learn more about your ad-choices at https://www.iheartpodcastnetwork.comSee omnystudio.com/listener for privacy information.
Trends in Natural Language Processing with Sameer Singh - #445
Today we continue the 2020 AI Rewind series, joined by friend of the show Sameer Singh, an Assistant Professor in the Department of Computer Science at UC Irvine.
We last spoke with Sameer at our Natural Language Processing office hours back at TWIMLfest, and was the perfect person to help us break down 2020 in NLP. Sameer tackles the review in 4 main categories, Massive Language Modeling, Fundamental Problems with Language Models, Practical Vulnerabilities with Language Models, and Evaluation.
We also explore the impact of GPT-3 and Transformer models, the intersection of vision and language models, and the injection of causal thinking and modeling into language models, and much more.
The complete show notes for this episode can be found at twimlai.com/go/445.
Beyond Accuracy: Behavioral Testing of NLP Models with Sameer Singh - #406
Today we’re joined by Sameer Singh, an assistant professor in the department of computer science at UC Irvine.
Sameer’s work centers on large-scale and interpretable machine learning applied to information extraction and natural language processing. We caught up with Sameer right after he was awarded the best paper award at ACL 2020 for his work on Beyond Accuracy: Behavioral Testing of NLP Models with CheckList.
In our conversation, we explore CheckLists, the task-agnostic methodology for testing NLP models introduced in the paper. We also discuss how well we understand the cause of pitfalls or failure modes in deep learning models, Sameer’s thoughts on embodied AI, and his work on the now famous LIME paper, which he co-authored alongside Carlos Guestrin.
The complete show notes for this episode can be found at twimlai.com/go/406.
Working with the Large Hadron Collider
Jonathan is joined by Daniel Whiteson of Daniel and Jorge Explain the Universe. Daniel works in the field of experimental particle physics and conducts research using the LHC.
Learn more about your ad-choices at https://www.iheartpodcastnetwork.comSee omnystudio.com/listener for privacy information.
Deep Reinforcement Learning Primer and Research Frontiers with Kamyar Azizzadenesheli - TWiML Talk #177
Today we’re joined by Kamyar Azizzadenesheli, PhD student at the University of California, Irvine, who joins us to review the core elements of RL, along with a pair of his RL-related papers: “Efficient Exploration through Bayesian Deep Q-Networks” and “Sample-Efficient Deep RL with Generative Adversarial Tree Search.”
To skip the Deep Reinforcement Learning primer conversation and jump to the research discussion, skip to the 34:30 mark of the episode. Show notes at https://twimlai.com/talk/177