A Modular Connectionist Architecture for Control

这笔赠款将支持机器学习控制的研究 非线性动力学系统。 乔丹医生和雅各布斯医生 研究多网络连接主义体系结构， 分段控制策略，比较备选分解 控制任务，同时学习多个任务。 他们希望多网络能够表现出更快的学习速度，更好的 泛化，更可解释的表示，等等 比单个神经网络更有效地使用硬件。

This grant will support research in machine learning for control of nonlinear dynamical systems. Drs. Jordan and Jacobs will study multinetwork connectionist architectures for discovering picewise control strategies, comparing alternative decompositions of control tasks, and learning multiple tasks simultaneously. They expect multinetworks to show faster learning rates, better generalization, more interpretable representations, and more efficient use of hardware than single neural networks.