Concepts, Properties and an Approach for Compositional Generalization

02/08/2021
by   Yuanpeng Li, et al.
0

Compositional generalization is the capacity to recognize and imagine a large amount of novel combinations from known components. It is a key in human intelligence, but current neural networks generally lack such ability. This report connects a series of our work for compositional generalization, and summarizes an approach. The first part contains concepts and properties. The second part looks into a machine learning approach. The approach uses architecture design and regularization to regulate information of representations. This report focuses on basic ideas with intuitive and illustrative explanations. We hope this work would be helpful to clarify fundamentals of compositional generalization and lead to advance artificial intelligence.

READ FULL TEXT

page 2

page 12

research
07/10/2023

Compositional Generalization from First Principles

Leveraging the compositional nature of our world to expedite learning an...
research
12/08/2020

Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization

Human intelligence exhibits compositional generalization (i.e., the capa...
research
10/07/2019

Compositional Generalization for Primitive Substitutions

Compositional generalization is a basic mechanism in human language lear...
research
10/02/2022

Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language

Deep learning models struggle with compositional generalization, i.e. th...
research
05/29/2023

Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization

Recognizing elementary underlying concepts from observations (disentangl...
research
06/16/2020

A Study of Compositional Generalization in Neural Models

Compositional and relational learning is a hallmark of human intelligenc...
research
06/06/2017

Deep Learning: Generalization Requires Deep Compositional Feature Space Design

Generalization error defines the discriminability and the representation...

Please sign up or login with your details

Forgot password? Click here to reset