Search Results for author:
Found 5 papers, 0 papers with code
Head2Toe: Utilizing Intermediate Representations for Better OOD Generalization
We propose a method, Head-to-Toe probing (Head2Toe), that selects features from all layers of the source model to train a classification head for the target-domain.
Discrete-Valued Neural Communication
Deep learning has advanced from fully connected architectures to structured models organized into components, e. g., the transformer composed of positional elements, modular architectures divided into slots, and graph neural nets made up of nodes.
Dependency Structure Discovery from Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments
To use a video game as an illustration, two enemies of the same type will share schemata but will have separate object files to encode their distinct state (e. g., health, position).
Transforming neural network visual representations to predict human judgments of similarity
Deep-learning vision models have shown intriguing similarities and differences with respect to human vision.
