4 papers · 1 filter
Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models
Can Demircan, Tankred Saanum, Akshay K. Jagadish +2
In-context learning, the ability to adapt based on a few examples in the input prompt, is a ubiquitous feature of large language models (LLMs). However, as LLMs' in-context learnin…
Stochastic Gradient Descent Captures How Children Learn About Physics
Luca M. Schulze Buschoff, Eric Schulz, Marcel Binz
As children grow older, they develop an intuitive understanding of the physical processes around them. They move along developmental trajectories, which have been mapped out extens…
Emulating Human Developmental Stages with Bayesian Neural Networks
Marcel Binz, Dominik Endres
We compare the acquisition of knowledge in humans and machines. Research from the field of developmental psychology indicates, that human-employed hypothesis are initially guided b…
Where Do Human Heuristics Come From?
Marcel Binz, Dominik Endres
Human decision-making deviates from the optimal solution, that maximizes cumulative rewards, in many situations. Here we approach this discrepancy from the perspective of bounded r…