Neural Network Dynamics and Computation, Institute of Genetics, University of Bonn, 53115 Bonn, Germany.
Department of Computer Science, and Neuroscience Institute, University of Sheffield, Sheffield S1 4DP, United Kingdom.
Phys Rev Lett. 2020 Aug 21;125(8):088103. doi: 10.1103/PhysRevLett.125.088103.
The ability of humans and animals to quickly adapt to novel tasks is difficult to reconcile with the standard paradigm of learning by slow synaptic weight modification. Here, we show that fixed-weight neural networks can learn to generate required dynamics by imitation. After appropriate weight pretraining, the networks quickly and dynamically adapt to learn new tasks and thereafter continue to achieve them without further teacher feedback. We explain this ability and illustrate it with a variety of target dynamics, ranging from oscillatory trajectories to driven and chaotic dynamical systems.
人类和动物能够快速适应新任务的能力，与通过缓慢的突触权重修改进行学习的标准模式很难协调。在这里，我们表明，固定权重的神经网络可以通过模仿来学习生成所需的动力学。在适当的权重预训练后，网络可以快速动态地适应学习新任务，此后无需进一步的教师反馈即可继续完成任务。我们解释了这种能力，并通过各种目标动力学进行了说明，范围从振荡轨迹到驱动和混沌动力学系统。
