3 papers
cs.LG2025
Training the Untrainable: Introducing Inductive Bias via Representational Alignment
Vighnesh Subramaniam, David Mayo, Colin Conwell +4
We demonstrate that architectures which traditionally are considered to be ill-suited for a task can be trained using inductive biases from another architecture. We call a network…
cs.LG2024
BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?
David Mayo, Christopher Wang, Asa Harbin +4
When evaluating stimuli reconstruction results it is tempting to assume that higher fidelity text and image generation is due to an improved understanding of the brain or more powe…
cs.CV2024
Using Multimodal Deep Neural Networks to Disentangle Language from Visual Aesthetics
Colin Conwell, Christopher Hamblin, Chelsea Boccagno +4
When we experience a visual stimulus as beautiful, how much of that experience derives from perceptual computations we cannot describe versus conceptual knowledge we can readily tr…