139 citations · 462 across the 39 of their papers we have counts for
5 papers · 1 filter
Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
Gianluca Bencomo, Max Gupta, Ioana Marinescu +2
Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon…
What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions
Liyi Zhang, Michael Y. Li, R. Thomas McCoy +3
Autoregressive language models have demonstrated a remarkable ability to extract latent structure from text. The embeddings from large language models have been shown to capture as…
Distilling Symbolic Priors for Concept Learning into Neural Networks
Ioana Marinescu, R. Thomas McCoy, Thomas L. Griffiths
Humans can learn new concepts from a small number of examples by drawing on their inductive biases. These inductive biases have previously been captured by using Bayesian models de…
Bayes in the age of intelligent machines
Thomas L. Griffiths, Jian-Qiao Zhu, Erin Grant +1
The success of methods based on artificial neural networks in creating intelligent machines seems like it might pose a challenge to explanations of human cognition in terms of Baye…
Discovering the Compositional Structure of Vector Representations with Role Learning Networks
Paul Soulos, Tom McCoy, Tal Linzen +1
How can neural networks perform so well on compositional tasks even though they lack explicit compositional representations? We use a novel analysis technique called ROLE to show t…