Timezone: »

 
Poster
Bridging Machine Learning and Logical Reasoning by Abductive Learning
Wang-Zhou Dai · Qiuling Xu · Yang Yu · Zhi-Hua Zhou

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #157
in Deep Learning -- Efficient Training Methods »

Perception and reasoning are two representative abilities of intelligence that are integrated seamlessly during human problem-solving processes. In the area of artificial intelligence (AI), the two abilities are usually realised by machine learning and logic programming, respectively. However, the two categories of techniques were developed separately throughout most of the history of AI. In this paper, we present the abductive learning targeted at unifying the two AI paradigms in a mutually beneficial way, where the machine learning model learns to perceive primitive logic facts from data, while logical reasoning can exploit symbolic domain knowledge and correct the wrongly perceived facts for improving the machine learning models. Furthermore, we propose a novel approach to optimise the machine learning model and the logical reasoning model jointly. We demonstrate that by using abductive learning, machines can learn to recognise numbers and resolve unknown mathematical operations simultaneously from images of simple hand-written equations. Moreover, the learned models can be generalised to longer equations and adapted to different tasks, which is beyond the capability of state-of-the-art deep learning models.

Keywords: Problem Solving · Neuroscience and Cognitive Science · Algorithms -> Classification; Deep Learning -> Predictive Models; Neuroscience and Cognitive Science · Human or Animal Learnin
[ Paper]  [ Slides] 

Author Information

Wang-Zhou Dai (Imperial College London)
Qiuling Xu (Purdue University)
Yang Yu (Nanjing University)
Zhi-Hua Zhou (Nanjing University)

More from the Same Authors