Tunneling Neural Perception and Logic Reasoning through Abductive Learning
This work addresses the problem of joint perception and reasoning in AI systems, which currently require human intervention, by introducing a novel framework that could advance towards human-level learning ability.
The paper tackles the incompatibility between perception and reasoning modules in machine learning by proposing the abductive learning framework, which learns both simultaneously through a trial-and-error process, enabling generalization from a small set of hand-written equations to complex ones beyond state-of-the-art neural networks.
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.