Memory Networks

By Jason Weston et al
Published on Nov. 29, 2015
Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction, 2. Memory Networks, 3. A MemNN Implementation for Text, 4. Related Work, 5. Experiments

Summary

Memory Networks describe a new class of learning models that reason with inference components combined with a long-term memory component. They investigate these models in the context of question answering, where the long-term memory acts as a knowledge base. The paper discusses the framework, implementation, experiments, and related works in detail.
×
This is where the content will go.