Search Results for author:
Found 5 papers, 2 papers with code
Getting aligned on representational alignment
Finally, we lay out open problems in representational alignment where progress can benefit all three of these fields.
VICE: Variational Interpretable Concept Embeddings
This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task.
Semantic features of object concepts generated with GPT-3
Given recent promising developments with transformer-based language models, here we asked whether it was possible to use such models to automatically generate meaningful lists of properties for arbitrary object concepts and whether these models would produce features similar to those found in humans.
Revealing interpretable object representations from human behavior
To study how mental object representations are related to behavior, we estimated sparse, non-negative representations of objects using human behavioral judgments on images representative of 1, 854 object categories.
The Same Analysis Approach: Practical protection against the pitfalls of novel neuroimaging analysis methods
We stress the importance of keeping the analysis method the same in main and test analyses, because only this way possible confounds and unexpected properties can be reliably detected and avoided.
Neurons and Cognition Applications
