Tunneling Neural Perception and Logic Reasoning through Abductive Learning

By Wang-Zhou Dai, Qiu-Ling Xu, Yang Yu, Zhi-Hua Zhou. 2018

24 citations recorded by the source corpus.

Perception and reasoning are basic human abilities that are seamlessly connected as part of human intelligence. However, in current machine learning systems, the perception and reasoning modules are incompatible. Tasks requiring joint perception and reasoning ability are difficult to accomplish autonomously and still demand human intervention. Inspired by the way language experts decoded Mayan scripts by joining two abilities in an abductive manner, this paper proposes the abductive learning framework. The framework learns perception and reasoning simultaneously with the help of a trial-and-error abductive process. We present the Neural-Logical Machine as an implementation of this novel learning framework. We demonstrate that--using human-like abductive learning--the machine learns from a small set of simple hand-written equations and then generalizes well to complex equations, a feat that is beyond the capability of state-of-the-art neural network models. The abductive learning framework explores a new direction for approaching human-level learning ability.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Program Analysis & Verification

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sebastijan Dumancic
2. Angelika Kimmig
3. Robin Manhaeve
4. Luc De Raedt
5. Thomas Demeester
6. Denny Zhou
7. Zico Kolter
8. Jiayuan Mao

In Computer Vision and Pattern Recognition

1. Zico Kolter
2. Jiayuan Mao
3. Thomas Demeester
4. Po-Wei Wang
5. Luc De Raedt
6. Tian Lin
7. Chong Wang
8. Angelika Kimmig

In Natural Language Processing

1. Jiayuan Mao
2. Thomas Demeester
3. Luc De Raedt
4. Tian Lin
5. Chong Wang
6. Angelika Kimmig
7. Sebastijan Dumancic
8. Robin Manhaeve

In Program Analysis & Verification

1. Zico Kolter
2. Jiayuan Mao

Citations in the corpus

• Neural Logic Machines (2019, background): “Dai et al. (2018) combines structured visual representation and theorem proving.”
• DeepProbLog: Neural Probabilistic Logic Programming (2018, methodology): “Dai et al. [2018] show a different way to combine perception with reasoning.”
• SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver (2019, background): “…focused on creating differentiable modules from an existing set of known relationships , so that a deep network can learn the parameters of these relationships (Dai et al., 2018; Manhaeve et al., 2018; Sourek et al., 2018; Xu et al., 2018; Hu et al., 2016; Yang et al., 2017; Selsam et al., 2018).”