一个在开放二维的视觉环境中进行灵活任务学习的有效模式
A Useful Motif for Flexible Task Learning in an Embodied Two-Dimensional Visual Environment
摘要：
动物（尤其是人类）有一种惊人的能力，可以快速学习新任务，并在它们之间灵活切换。大脑如何支持这种能力在很大程度上是未知的，无论是神经科学还是算法。一个合理的假设是，在每个任务的基础上动态地分配基于底层通用感官表征的模块。神经科学和人工智能的最新结果表明，通用视觉表示的作用可能由深度卷积神经网络发挥，并给出了一些线索，如何发现和构建基于这种表示的任务模块。在这项工作中，我们调查模块架构在一个具体的二维的【形】触摸屏环境中，其中代理的学习必须通过与环境，发出图像和奖励，并接受触摸作为输入的交互发生。该环境旨在捕捉视觉神经科学和心理物理学中通常部署的任务环境的物理结构。我们表明，在这种情况下，非常简单的变化，这样的模块使用的非线性激活可以显着影响它是如何快速学习视觉任务，以及它是如何适合切换到新的任务。
英文摘要：
Animals (especially humans) have an amazing ability to learn new tasks quickly, and switch between them flexibly. How brains support this ability is largely unknown, both neuroscientifically and algorithmically. One reasonable supposition is that modules drawing on an underlying general-purpose sensory representation are dynamically allocated on a per-task basis. Recent results from neuroscience and artificial intelligence suggest the role of the general purpose visual representation may be played by a deep convolutional neural network, and give some clues how task modules based on such a representation might be discovered and constructed. In this work, we investigate module architectures in an embodied two-dimensional touchscreen environment, in which an agent's learning must occur via interactions with an environment that emits images and rewards, and accepts touches as input. This environment is designed to capture the physical structure of the task environments that are commonly deployed in visual neuroscience and psychophysics. We show that in this context, very simple changes in the nonlinear activations used by such a module can significantly influence how fast it is at learning visual tasks and how suitable it is for switching to new tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
