Engineering neural systems for high-level problem solving

• Published in: Neural networks Vol. 79; pp. 37 - 52
• Main Authors: Sylvester, Jared, Reggia, James
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.07.2016
• Subjects: Algorithms; Artificial Intelligence; Attention; Attractor neural networks; Cards; Control systems; Engineering - methods; Gated neural networks; Human performance; Humans; Matching; Neural network problem solving; Neural networks; Neural Networks (Computer); Neuroengineering; Photic Stimulation - methods; Problem Solving; Tasks; Top-down vs. bottom-up AI; Neuroengineering; Top-down vs. bottom-up AI; Attractor neural networks; Neural network problem solving; Gated neural networks
• ISSN: 0893-6080; 1879-2782
• DOI: 10.1016/j.neunet.2016.03.006

There is a long-standing, sometimes contentious debate in AI concerning the relative merits of a symbolic, top-down approach vs. a neural, bottom-up approach to engineering intelligent machine behaviors. While neurocomputational methods excel at lower-level cognitive tasks (incremental learning for pattern classification, low-level sensorimotor control, fault tolerance and processing of noisy data, etc.), they are largely non-competitive with top-down symbolic methods for tasks involving high-level cognitive problem solving (goal-directed reasoning, metacognition, planning, etc.). Here we take a step towards addressing this limitation by developing a purely neural framework named galis. Our goal in this work is to integrate top-down (non-symbolic) control of a neural network system with more traditional bottom-up neural computations. galis is based on attractor networks that can be “programmed” with temporal sequences of hand-crafted instructions that control problem solving by gating the activity retention of, communication between, and learning done by other neural networks. We demonstrate the effectiveness of this approach by showing that it can be applied successfully to solve sequential card matching problems, using both human performance and a top-down symbolic algorithm as experimental controls. Solving this kind of problem makes use of top-down attention control and the binding together of visual features in ways that are easy for symbolic AI systems but not for neural networks to achieve. Our model can not only be instructed on how to solve card matching problems successfully, but its performance also qualitatively (and sometimes quantitatively) matches the performance of both human subjects that we had perform the same task and the top-down symbolic algorithm that we used as an experimental control. We conclude that the core principles underlying the galis framework provide a promising approach to engineering purely neurocomputational systems for problem-solving tasks that in people require higher-level cognitive functions.