Analyzing Learned Molecular Representations for Property Prediction

Selection of Molecular Descriptor Subsets for Property Prediction

Geodesics of learned representations

We develop a new method for visualizing and refining the invariances of learned representations. Given two reference images (typically, differing by some transformation), we synthesize a sequence of images lying on a path between them that is of minimal length in the space of a representation (a “representational geodesic”). If the transformation relating the two reference images is an invarian...

Analyzing Action Representations

We argue that actions represent the basic seed of intelligence underlying perception of the environment, and the representations encoding actions should be the starting point upon which further studies of cognition are built. In this paper we make a rst eeort in characterizing these action representations. In particular, from the study of simple actions related to 3D rigid motion interpretation...

Sparse Learned Representations for Image Restoration

Sparse representations of signals have drawn considerable interest in recent years. The assumption that natural signals, such as images, admit a sparse decomposition over a redundant dictionary leads to efficient algorithms for handling such sources of data. In particular, the design of well adapted dictionaries for images has been a major challenge. The K-SVD has been recently proposed for thi...

Updating representations of learned scenes.

Two experiments were designed to compare scene recognition reaction time (RT) and accuracy patterns following observer versus scene movement. In Experiment 1, participants memorized a scene from a single perspective. Then, either the scene was rotated or the participants moved (0 degrees -360 degrees in 36 degrees increments) around the scene, and participants judged whether the objects' positi...