A Brain-inspired Memory Transformation based Differentiable Neural Computer for Reasoning-based Question Answering

TL;DR

This paper introduces a brain-inspired Memory Transformation DNC model that enhances reasoning and question answering by effectively transforming and utilizing memory, leading to improved performance and robustness.

Contribution

It proposes a novel Memory Transformation mechanism integrating working and long-term memory into DNC, inspired by brain functions, to improve reasoning and learning efficiency.

Findings

Achieves superior performance on bAbI question answering tasks

Demonstrates faster convergence compared to existing DNC models

Memory transformation improves robustness and stability of reasoning

Abstract

Reasoning and question answering as a basic cognitive function for humans, is nevertheless a great challenge for current artificial intelligence. Although the Differentiable Neural Computer (DNC) model could solve such problems to a certain extent, the development is still limited by its high algorithm complexity, slow convergence speed, and poor test robustness. Inspired by the learning and memory mechanism of the brain, this paper proposed a Memory Transformation based Differentiable Neural Computer (MT-DNC) model. MT-DNC incorporates working memory and long-term memory into DNC, and realizes the autonomous transformation of acquired experience between working memory and long-term memory, thereby helping to effectively extract acquired knowledge to improve reasoning ability. Experimental results on bAbI question answering task demonstrated that our proposed method achieves superior performance and faster convergence speed compared to other existing DNN and DNC models. Ablation studies also indicated that the memory transformation from working memory to long-term memory plays essential role in improving the robustness and stability of reasoning. This work explores how brain-inspired memory transformation can be integrated and applied to complex intelligent dialogue and reasoning systems.