非概率反馈训练的一般神经网络中的有效概率推理
Efficient Probabilistic Inference in Generic Neural Networks Trained with Non-Probabilistic Feedback
摘要:
动物在广泛的心理物理任务中执行接近最佳的概率推理。概率推理需要对与任务变量相关的不确定性进行逐个试验的表示,并随后使用这种表示。以前的工作已经实现了这样的计算使用神经网络与手工制作和任务相关的操作。我们表明,一般的神经网络训练一个简单的基于错误的学习规则执行接近最佳的概率推理在9个常见的心理物理任务。在概率分类任务中,基于错误的学习在一个通用的网络同时解释了猴子的学习曲线和其选择行为的定性方面的演变。在所有任务中,给定性能水平所需的神经元数量随着输入种群大小呈次线性增长,这是对以前概率推理实现的重大改进。经过训练的网络开发了一种新的基于稀疏性的概率种群代码。我们的研究结果表明,概率推理自然出现在通用神经网络训练与基于错误的学习规则。
英文摘要:
Animals perform near-optimal probabilistic inference in a wide range of psychophysical tasks. Probabilistic inference requires trial-to-trial representation of the uncertainties associated with task variables and subsequent use of this representation. Previous work has implemented such computations using neural networks with hand-crafted and task-dependent operations. We show that generic neural networks trained with a simple error-based learning rule perform near-optimal probabilistic inference in nine common psychophysical tasks. In a probabilistic categorization task, error-based learning in a generic network simultaneously explains a monkey's learning curve and the evolution of qualitative aspects of its choice behavior. In all tasks, the number of neurons required for a given level of performance grows sub-linearly with the input population size, a substantial improvement on previous implementations of probabilistic inference. The trained networks develop a novel sparsity-based probabilistic population code. Our results suggest that probabilistic inference emerges naturally in generic neural networks trained with error-based learning rules.
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。