A Modular Connectionist Architecture for Control

这笔拨款将用于支持机器学习控制非线性动力系统的研究。乔丹博士和雅各布斯博士将研究多网络连接主义架构，以发现图像化的控制策略，比较控制任务的不同分解，并同时学习多项任务。他们预计，与单一的神经网络相比，多个网络将显示出更快的学习速度、更好的泛化、更易解释的表示法以及更高效的硬件使用。

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.