Detect, understand, act: A neuro-symbolic hierarchical reinforcement learning framework

L Mitchener, D Tuckey, M Crosby, A Russo - Machine Learning, 2022‏ - Springer
In this paper we introduce Detect, Understand, Act (DUA), a neuro-symbolic reinforcement
learning framework. The Detect component is composed of a traditional computer vision …

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

N Cingillioglu, A Russo - arxiv preprint arxiv:2106.07487, 2021‏ - arxiv.org
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 …

Detect, Understand, Act: A Neuro-symbolic Hierarchical Reinforcement Learning Framework

M Ludovico, D Tuckey, M Crosby… - Machine Learning, 2022‏ - search.proquest.com
In this paper we introduce Detect, Understand, Act (DUA), a neuro-symbolic reinforcement
learning framework. The Detect component is composed of a traditional computer vision …

[PDF][PDF] Automatic Concept Extraction and Its Use in Explaining Video Classification

R Parać, A Russo, L Dickens, R Chatley - 2022‏ - imperial.ac.uk
For most tasks, fully neural architectures are undisputedly the best performing and most
widely used models in machine learning. However, they are mostly uninterpretable, making …