python

A Study of Compositional Generalization in Neural Models

A framework to study how neural models generalize in compositional, relational domains.

Transfer Learning in Visual and Relational Reasoning

A proposed Transfer Learning taxonomy for Visual Reasoning and a new State-of-the-Art model.

The Transformer Model

Learning about the Attention Mechanism and the Transformer Model.

MI-Prometheus

Enabling reproducible Machine Learning research.

On Transfer Learning using a MAC model variant

A simplified variant of the MAC model that achieves comparable accuracy, while training faster.

Accelerating Machine Learning Research with MI-Prometheus

The paper presents a PyTorch-based, open-source framework for Machine Learning.