Griffiths Computational Cognitive Science Lab

A schematic of our method. On the left are shown Bayesian inference (visualized using Bayes’ rule and a portrait of the Reverend Bayes) and neural networks (visualized as a weight matrix). Then, an arrow labeled “meta-learning” combines Bayesian inference and neural networks into a “prior-trained neural network”, described as a neural network that has the priors of a Bayesian model – visualized as the same portrait of Reverend Bayes but made out of numbers. Finally, an arrow labeled “learning” goes from the prior-trained neural network to two examples of what it can learn: formal languages (visualized with a finite-state automaton) and aspects of English syntax (visualized with a parse tree for the sentence “colorless green ideas sleep furiously”).

🤖🧠 Paper out in Nature Communications! 🧠🤖

Bayesian models can learn rapidly. Neural networks can handle messy, naturalistic data. How can we combine these strengths?

Our answer: Use meta-learning to distill Bayesian priors into a neural network!

www.nature.com/articles/s41...

1/n

🚨 New preprint alert! 🚨

Thrilled to share new research on teaching!
Work supervised by
@cocoscilab.bsky.social, @yaelniv.bsky.social, and @markkho.bsky.social.

This project asks:
When do people teach by mentalizing vs with heuristics? 1/3

osf.io/preprints/os...

🚨 New in Nature Human Behavior! 🚨

Binary climate data visuals amplify perceived impact of climate change.

Both graphs in this image reflect equivalent climate change trends over time, yet people consistently perceive climate change as having a greater impact in the right plot than the left.

👇1/n

New preprint shows that ideas from distributed systems can be used to predict when agents will adopt specialized strategies when working together to perform a task

The new AI Lab at Princeton has positions for AI Postdoctoral Research Fellows for three research initiatives: AI for Accelerating Invention, Natural and Artificial Minds, and Princeton Language and Intelligence. Deadline is 12/31. More information here: ai.princeton.edu/ai-lab/emplo...

My paper on hierarchical plans is out in Cognition!🎉

tldr: We ask participants to generate hierarchical plans in a programming game. People prefer to reuse beyond what standard accounts predict, which we formalize as induction of a grammar over actions.

authors.elsevier.com/a/1kBQr2Hx2x...

(5/5) Thanks to the many contributors to the book! @markkho.bsky.social @norijacoby.bsky.social @eringrant.bsky.social @fredcallaway.bsky.social @tomerullman.bsky.social @jhamrick.bsky.social @tobigerstenberg.bsky.social @spiantado.bsky.social
@noahdgoodman.bsky.social @ebonawitz.bsky.social

(4/5) Here's the table of contents. An Open Access version of the book is available through the MIT Press website.

(3/5) That same perspective is valuable for understanding modern AI systems. In particular, Bayesian models highlight the inductive biases that make it possible for humans to learn from small amounts of data, and give us tools for building machines with the same capacity.

(2/5) Bayesian models start by considering the abstract computational problems intelligent systems have to solve and then identifying their optimal solutions. Those solutions can help us understand why people do the things we do.

(1/5) Very excited to announce the publication of Bayesian Models of Cognition: Reverse Engineering the Mind. More than a decade in the making, it's a big (600+ pages) beautiful book covering both the basics and recent work: mitpress.mit.edu/978026204941...

(1) Vision language models can explain complex charts & decode memes, but struggle with simple tasks young kids find easy - like counting objects or finding items in cluttered scenes! Our 🆒🆕 #NeurIPS2024 paper shows why: they face the same 'binding problem' that constrains human vision! 🧵👇

We are advertising a new postdoctoral position in computational cognitive science, with specific interest in applications of large language models in cognitive science and use of Bayesian methods and metalearning to understand human cognition and AI systems. www.princeton.edu/acad-positio...

First post! Does the success of deep neural networks in creating AI systems mean Bayesian models are no longer relevant? Our new paper argues the opposite: these approaches are complementary, creating new opportunities to use Bayes to understand intelligent machines
arxiv.org/abs/2311.10206