Neural Meta-Symbolic Reasoning and Learning
This work addresses the challenge of making deep learning more efficient and generalizable, which is crucial for advancing AI towards human-like problem-solving abilities, though it appears incremental in combining neural and symbolic approaches.
The paper tackles the problem of enabling deep learning systems to perform general intelligence tasks with limited computation and data by introducing NEMESYS, a neural meta-symbolic system that uses differentiable forward-chaining reasoning in first-order logic, allowing it to adapt to various tasks without modifying the internal reasoning system and learn meta-level programs from examples.
Deep neural learning uses an increasing amount of computation and data to solve very specific problems. By stark contrast, human minds solve a wide range of problems using a fixed amount of computation and limited experience. One ability that seems crucial to this kind of general intelligence is meta-reasoning, i.e., our ability to reason about reasoning. To make deep learning do more from less, we propose the first neural meta-symbolic system (NEMESYS) for reasoning and learning: meta programming using differentiable forward-chaining reasoning in first-order logic. Differentiable meta programming naturally allows NEMESYS to reason and learn several tasks efficiently. This is different from performing object-level deep reasoning and learning, which refers in some way to entities external to the system. In contrast, NEMESYS enables self-introspection, lifting from object- to meta-level reasoning and vice versa. In our extensive experiments, we demonstrate that NEMESYS can solve different kinds of tasks by adapting the meta-level programs without modifying the internal reasoning system. Moreover, we show that NEMESYS can learn meta-level programs given examples. This is difficult, if not impossible, for standard differentiable logic programming