paper-with-me

홈 › Papers

Constellation: Learning relational abstractions over objects for compositional imagination

2021-07-23 · James C. R. Whittington, Rishabh Kabra, Loic Matthey, Christopher P. Burgess, Alexander Lerchner

Learning structured representations of visual scenes is currently a major bottleneck to bridging perception with reasoning. While there has been exciting progress with slot-based models, which learn to segment scenes into sets of objects, learning configurational properties of entire groups of objects is still under-explored. To address this problem, we introduce Constellation, a network that learns relational abstractions of static visual scenes, and generalises these abstractions over sensory particularities, thus offering a potential basis for abstract relational reasoning. We further show that this basis, along with language association, provides a means to imagine sensory content in new ways. This work is a first step in the explicit representation of visual relationships and using them for complex cognitive procedures.

📄 PDF Abstract BibTeX arXiv:2107.11153

Code (0)

등록된 구현이 없습니다.

Tasks

Relational Reasoning

Similar Papers 제목 키워드 기반

Compositional diversity in visual concept learning

2023-05-30 · Yanli Zhou, Reuben Feinman, Brenden M. Lake

Humans leverage compositionality to efficiently learn new concepts, understanding how familiar parts can combine together to form novel objects. In contrast, popular computer vision models struggle to make the same types…

DiversityProgram induction

Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems

2022-04-27 · Rushang Karia, Siddharth Srivastava

Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes relational abstractions in conjunction with …

Objectreinforcement-learningReinforcement LearningReinforcement Learning (RL)

A Study of Compositional Generalization in Neural Models

2020-06-16 · Tim Klinger, Dhaval Adjodah, Vincent Marois, Josh Joseph 외

Compositional and relational learning is a hallmark of human intelligence, but one which presents challenges for neural models. One difficulty in the development of such models is the lack of benchmarks with clear compos…

image-classificationImage ClassificationRelational Reasoning

Compositional Abstractions of Interconnected Discrete-Time Switched Systems

2021-09-28 · Abdalla Swikir, Majid Zamani

In this paper, we introduce a compositional method for the construction of finite abstractions of interconnected discrete-time switched systems. Particularly, we use a notion of so-called alternating simulation function …

Relation

Answer-Set-Programming-based Abstractions for Reinforcement Learning

2026-05-29 · Rafael Bankosegger, Thomas Eiter, Johannes Oetsch arxiv

Reinforcement Learning (RL) enables autonomous agents to learn policies from experience, but realistic problems often involve enormous state spaces, making learning and generalisation challenging. Abstraction and approxi…

Reinforcement Learning