Anna C. Schapiro

TL;DR: It is argued that a deep network is best understood in terms of components used to design it—objective functions, architecture and learning rules—rather than unit-by-unit computation.

TL;DR: A computational account of how the relevant representations might arise is presented, proposing a direct connection between event learning and the learning of semantic categories.

TL;DR: It is suggested that object representations in MTL come to mirror the temporal structure of the environment, supporting rapid and incidental statistical learning.

TL;DR: This article exposed a neural network model that instantiates known properties of hippocampal projections and subfields to sequences of items with temporal regularities and found that the monosynaptic pathway—the pathway connecting entorhinal cortex directly to region CA1—was able to support statistical learning, while the trisynaptic pathways learned individual episodes.

TL;DR: Findings provide converging support for the importance of the MTL in extracting temporal regularities, in a case study of LSJ, a patient with complete bilateral hippocampal loss and broader MTL damage.