Goal-driven deep learning increasingly supplements classical modeling approaches in computational neuroscience. The strength of deep neural networks as models of the brain lies in their ability to autonomously learn the connectivity required to solve complex and ecologically valid tasks, obviating the need for hand-engineered or hypothesis-driven connectivity patterns. Consequently, goal-driven models can generate hypotheses about the neurocomputations underlying cortical processing that are grounded in macro- and mesoscopic anatomical properties of the network's biological counterpart. Whereas, goal-driven modeling is already becoming prevalent in the neuroscience of perception, its application to the sensorimotor domain is currently hampered by the complexity of the methods required to train models comprising the closed sensation-action loop. This paper describes AngoraPy, a Python library that mitigates this obstacle by providing researchers with the tools necessary to train complex recurrent convolutional neural networks that model the human sensorimotor system. To make the technical details of this toolkit more approachable, an illustrative example that trains a recurrent toy model on in-hand object manipulation accompanies the theoretical remarks. An extensive benchmark on various classical, 3D robotic, and anthropomorphic control tasks demonstrates AngoraPy's general applicability to a wide range of tasks. Together with its ability to adaptively handle custom architectures, the flexibility of this toolkit demonstrates its power for goal-driven sensorimotor modeling.

中文翻译：

---

AngoraPy：用于对拟人目标驱动的感觉运动系统进行建模的 Python 工具包

目标驱动的深度学习越来越多地补充计算神经科学中的经典建模方法。深度神经网络作为大脑模型的优势在于它们能够自主学习解决复杂且生态上有效的任务所需的连接，从而无需手工设计或假设驱动的连接模式。因此，目标驱动模型可以生成关于皮层处理基础神经计算的假设，这些假设基于网络生物对应物的宏观和中观解剖特性。尽管目标驱动建模在感知神经科学中已经变得普遍，但其在感觉运动领域的应用目前受到训练包含闭合感觉-动作循环的模型所需方法的复杂性的阻碍。本文描述了安哥拉皮，一个 Python 库，通过为研究人员提供训练模拟人类感觉运动系统的复杂循环卷积神经网络所需的工具来缓解这一障碍。为了使该工具包的技术细节更容易理解，在理论说明的同时还提供了一个说明性示例，该示例用于训练手动对象操作的循环玩具模型。针对各种经典、3D 机器人和拟人化控制任务的广泛基准测试证明了 AngoraPy 对各种任务的普遍适用性。加上其自适应处理自定义架构的能力，该工具包的灵活性证明了其目标驱动的感觉运动建模的强大功能。