pix2rule: End-to-end Neuro-symbolic Rule Learning

06/14/2021
by   Nuri Cingillioglu, et al.
0

Humans have the ability to seamlessly combine low-level visual input with high-level symbolic reasoning often in the form of recognising objects, learning relations between them and applying rules. Neuro-symbolic systems aim to bring a unifying approach to connectionist and logic-based principles for visual processing and abstract reasoning respectively. This paper presents a complete neuro-symbolic method for processing images into objects, learning relations and logical rules in an end-to-end fashion. The main contribution is a differentiable layer in a deep learning architecture from which symbolic relations and rules can be extracted by pruning and thresholding. We evaluate our model using two datasets: subgraph isomorphism task for symbolic rule learning and an image classification domain with compound relations for learning objects, relations and rules. We demonstrate that our model scales beyond state-of-the-art symbolic learners and outperforms deep relational neural network architectures.

READ FULL TEXT

page 3

page 5

page 8

page 24

page 37

page 38

page 39

page 41

research
06/01/2021

Learning Representations for Sub-Symbolic Reasoning

Neuro-symbolic methods integrate neural architectures, knowledge represe...
research
11/26/2019

Logical Interpretations of Autoencoders

The unification of low-level perception and high-level reasoning is a lo...
research
12/05/2018

Photo-Realistic Blocksworld Dataset

In this report, we introduce an artificial dataset generator for Photo-r...
research
10/19/2020

ERIC: Extracting Relations Inferred from Convolutions

Our main contribution is to show that the behaviour of kernels across mu...
research
05/26/2021

TexRel: a Green Family of Datasets for Emergent Communications on Relations

We propose a new dataset TexRel as a playground for the study of emergen...
research
06/16/2021

Techniques for Symbol Grounding with SATNet

Many experts argue that the future of artificial intelligence is limited...
research
02/24/2020

Symbolic Learning and Reasoning with Noisy Data for Probabilistic Anchoring

Robotic agents should be able to learn from sub-symbolic sensor data, an...

Please sign up or login with your details

Forgot password? Click here to reset