A controller-peripheral architecture and costly energy principle for learning

A controller-peripheral architecture and costly energy principle for learning
复制标题

DOI:
10.1101/2023.01.16.524194
复制
发表时间:
2023-08
期刊:
bioRxiv
影响因子:
--
通讯作者:
Xiaoliang Luo;Robert M. Mok;Brett D. Roads;B. Love
Xiaoliang Luo;Robert M. Mok;Brett D. Roads;B. Love
中科院分区:
其他
文献类型:
--
作者:
Xiaoliang Luo;Robert M. Mok;Brett D. Roads;B. Love

文献摘要

相似文献

复杂的行为得到多个大脑区域协调的支持。在没有小人的情况下,大脑区域如何协调?我们认为协调是通过控制器-外周结构实现的,在这种结构中,外周(例如腹侧视觉流)旨在向其控制器(例如海马体和前额叶皮质)提供所需的输入,同时花费最少的资源。我们在这个框架内开发了一个正式的模型,以解决多个大脑区域如何协调以支持从几个示例图像中快速学习。该模型捕捉到了控制器中较高级别的活动如何塑造较低级别的视觉表示,以与大脑平行测量的方式影响它们的精度和稀疏性。具体地说,外围设备编码的视觉信息达到支持控制器平滑操作所需的程度。通过梯度下降优化的替代模型不受体系结构的限制,无法解释人类的行为或大脑反应,而且,作为标准深度学习方法的典型,是不稳定的逐次试验学习者。虽然以前的工作提供了对特定官能的描述,如知觉、注意力和学习,但控制器-外设方法是朝着解决关于多个官能如何协调的下一代问题迈出的一步。
Complex behavior is supported by the coordination of multiple brain regions. How do brain regions coordinate absent a homunculus? We propose coordination is achieved by a controller-peripheral architecture in which peripherals (e.g., the ventral visual stream) aim to supply needed inputs to their controllers (e.g., the hippocampus and prefrontal cortex) while expending minimal resources. We developed a formal model within this framework to address how multiple brain regions coordinate to support rapid learning from a few example images. The model captured how higher-level activity in the controller shaped lower-level visual representations, affecting their precision and sparsity in a manner that paralleled brain measures. In particular, the peripheral encoded visual information to the extent needed to support the smooth operation of the controller. Alternative models optimized by gradient descent irrespective of architectural constraints could not account for human behavior or brain responses, and, typical of standard deep learning approaches, were unstable trial-by-trial learners. While previous work offered accounts of specific faculties, such as perception, attention, and learning, the controller-peripheral approach is a step toward addressing next generation questions concerning how multiple faculties coordinate.