Timezone: »

 
Poster
Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
Qing Li · Siyuan Huang · Yining Hong · Yixin Chen · Ying Nian Wu · Song-Chun Zhu

Tue Jul 14 09:00 AM -- 09:45 AM & Tue Jul 14 10:00 PM -- 10:45 PM (PDT) @ Virtual
in Poster Session 3 »

The goal of neural-symbolic computation is to integrate the connectionist and symbolist paradigms. Prior methods learn the neural-symbolic models using reinforcement learning (RL) approaches, which ignore the error propagation in the symbolic reasoning module and thus converge slowly with sparse rewards. In this paper, we address these issues and close the loop of neural-symbolic learning by (1) introducing the grammar model as a symbolic prior to bridge neural perception and symbolic reasoning, and (2) proposing a novel back-search algorithm which mimics the top-down human-like learning procedure to propagate the error through the symbolic reasoning module efficiently. We further interpret the proposed learning framework as maximum likelihood estimation using Markov chain Monte Carlo sampling and the back-search algorithm as a Metropolis-Hastings sampler. The experiments are conducted on two weakly-supervised neural-symbolic tasks: (1) handwritten formula recognition on the newly introduced HWF dataset; (2) visual question answering on the CLEVR dataset. The results show that our approach significantly outperforms the RL methods in terms of performance, converging speed, and data efficiency. Our code and data are released at https://liqing-ustc.github.io/NGS.

Keywords: Algorithms · Computer Vision · Neuroscience and Cognitive Science · Natural Language Processing / Dialogue · Applications - Computer Vision
[ Slides] 

Author Information

Qing Li (UCLA)
Siyuan Huang (UCLA)
Yining Hong (University of California, Los Angeles)
Yixin Chen (UCLA)
Ying Nian Wu (UCLA)
Song-Chun Zhu (UCLA)

More from the Same Authors