arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2109.01039q-bio.NC
收藏

基于错误还是基于目标?循环尖峰网络学习的统一框架

Error-based or target-based? A unifying framework for learning in recurrent spiking networks

Cristiano Capone, Paolo Muratore, Pier Stanislao Paolucci

摘要:

在生物或人工网络中学习意味着改变控制网络动态的规律,以便在特定情况下更好地表现。在监督学习领域,两种互补的方法脱颖而出:基于错误和基于目标的学习。然而,对于哪一个更适合哪一个任务,以及什么是最生物学上合理的,还没有达成共识。在这里,我们提出了一个全面的理论框架,包括这两个框架作为特殊情况。这种新颖的理论公式提供了两种方法之间的差异的主要见解。特别是,我们展示了如何基于目标的自然出现基于错误时,目标动态的约束的数量,并作为内部网络动态的结果,是可比的网络的自由度。此外,鉴于实验证据的相关性,尖峰在生物网络中,我们调查的作用,编码与特定模式的尖峰通过引入一个参数,定义的容忍度,在学习过程中精确的尖峰时间。我们的方法自然适用于模仿学习(特别是行为克隆),我们将其应用于解决相关的闭环任务,如按钮和食物任务和2D双足步行者。我们发现,一个高维反馈结构是非常重要的,当它是必要的,以解决一个任务,需要保留记忆很长一段时间(按钮和食物)。另一方面,我们发现,编码与特定模式的尖峰,使最佳性能的电机任务(2D双足步行者)。最后,我们表明,我们的理论公式建议协议推断的结构,在生物网络的学习反馈。

英文摘要:

Learning in biological or artificial networks means changing the laws governing the network dynamics in order to better behave in a specific situation. In the field of supervised learning, two complementary approaches stand out: error-based and target-based learning. However, there exists no consensus on which is better suited for which task, and what is the most biologically plausible. Here we propose a comprehensive theoretical framework that includes these two frameworks as special cases. This novel theoretical formulation offers major insights into the differences between the two approaches. In particular, we show how target-based naturally emerges from error-based when the number of constraints on the target dynamics, and as a consequence on the internal network dynamics, is comparable to the degrees of freedom of the network. Moreover, given the experimental evidences on the relevance that spikes have in biological networks, we investigate the role of coding with specific patterns of spikes by introducing a parameter that defines the tolerance to precise spike timing during learning. Our approach naturally lends itself to Imitation Learning (and Behavioral Cloning in particular) and we apply it to solve relevant closed-loop tasks such as the button-and-food task, and the 2D Bipedal Walker. We show that a high dimensionality feedback structure is extremely important when it is necessary to solve a task that requires retaining memory for a long time (button-and-food). On the other hand, we find that coding with specific patterns of spikes enables optimal performances in a motor task (the 2D Bipedal Walker). Finally, we show that our theoretical formulation suggests protocols to deduce the structure of learning feedback in biological networks.

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。

↑