←
Neil Bramley194 posts
Neil Bramley avatar

Neil Bramley

@NeilBramley

Find me on Bluesky

◷ Joined April 2009▧ 13 Photos and videos
Tomer Ullman avatar
⟳ Neil Bramley retweeted
Tomer Ullman@TomerUllman·15 Oct 2024

hooray, the "Bayesian Models of Cognition" book is out, for all your Bayesian models of cognition needs :) (I contributed to 3 chapters in the book -- development, intuitive physics, theory of mind -- that can be read on the ol' website)

Post attachment
Tia Gong avatar
⟳ Neil Bramley retweeted
Tia Gong@Tianwei_Gong·17 Apr 2024

So honoured to be one of the recipients of this award! ✨Thanks to my amazing supervisor @NeilBramley, my collaborators @tobigerstenberg, @mxpacer, @cocosci_lab, Ralf Mayrhofer, and the pioneers and current researchers in causal reasoning who have inspired this thesis! ✨

The Cognitive Science Society is thrilled to announce the winners of the 2024 Glushko Dissertation Prize! 🏆 Let’s meet the brilliant minds behind groundbreaking research in Cognitive Science 🧵👇

Post attachment
AK avatar
⟳ Neil Bramley retweeted
AK@_akhaliq·2 Feb 2024

SymbolicAI A framework for logic-based approaches combining generative models and solvers paper page: huggingface.co/papers/2402.0… introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the seamless integration of generative models with a diverse range of solvers by treating large language models (LLMs) as semantic parsers that execute tasks based on both natural and formal language instructions, thus bridging the gap between symbolic reasoning and generative AI. We leverage probabilistic programming principles to tackle complex tasks, and utilize differentiable and classical programming paradigms with their respective strengths. The framework introduces a set of polymorphic, compositional, and self-referential operations for data stream manipulation, aligning LLM outputs with user objectives. As a result, we can transition between the capabilities of various foundation models endowed with zero- and few-shot learning capabilities and specialized, fine-tuned models or solvers proficient in addressing specific problems. In turn, the framework facilitates the creation and evaluation of explainable computational graphs. We conclude by introducing a quality measure and its empirical score for evaluating these computational graphs, and propose a benchmark that compares various state-of-the-art LLMs across a set of complex workflows. We refer to the empirical score as the "Vector Embedding for Relational Trajectory Evaluation through Cross-similarity", or VERTEX score for short. The framework codebase and benchmark are linked below.

Post attachment
Brenden Lake avatar
⟳ Neil Bramley retweeted
Brenden Lake@LakeBrenden·1 Feb 2024

Published in Science today, @wkvong reports a dream experiment: he trained a multi-modal AI model from scratch on a subset of one child's experiences, as captured by headcam video. Shows how grounded word learning is possible in natural settings, as discussed in his thread:

1/ Today in Science, we train a neural net from scratch through the eyes and ears of one child. The model learns to map words to visual referents, showing how grounded language learning from just one child's perspective is possible with today's AI tools. science.org/doi/10.1126/scie…

Post attachment
Neil Bramley avatar
Neil Bramley@NeilBramley·23 Jan 2024

Paper lays out the approach and demonstrates with a bandit task case study complete with tutorial code and guidance for adapting to your own research questions!

Neil Bramley avatar
Neil Bramley@NeilBramley·23 Jan 2024

We train a neural network on data simulated from candidate models learning the relationship between design variables and expected info. The result: efficient experimental designs for modern research programs involving arbitrarily complex simulator models.

Neil Bramley avatar
Neil Bramley@NeilBramley·23 Jan 2024

Designing experiments to distinguish efficiently between candidate models or infer their parameters is great. Problem: Modern/interesting cognitive models typically lack closed form likelihoods, breaking standard approaches to Bayesian Optimal Experimental Design

Luiz Pessoa avatar
⟳ Neil Bramley retweeted
Luiz Pessoa@PessoaBrain·13 Jan 2024

𝗧𝗵𝗲 𝗢𝗻𝘁𝗼𝗹𝗼𝗴𝘆 𝗼𝗳 𝗖𝗼𝗺𝗽𝗹𝗲𝘅 𝗦𝘆𝘀𝘁𝗲𝗺𝘀: 𝗟𝗲𝘃𝗲𝗹𝘀 𝗼𝗳 𝗢𝗿𝗴𝗮𝗻𝗶𝘇𝗮𝘁𝗶𝗼𝗻, 𝗣𝗲𝗿𝘀𝗽𝗲𝗰𝘁𝗶𝘃𝗲𝘀, 𝗮𝗻𝗱 𝗖𝗮𝘂𝘀𝗮𝗹 𝗧𝗵𝗶𝗰𝗸𝗲𝘁𝘀 One of coolest figures in a philosophy paper... And one of most spectacular papers ever! cambridge.org/core/journals/…

Post attachment