Deep neural network models of sensory systems: windows onto the role of task constraints
Deep neural network models of sensory systems: windows onto the role of task constraints
复制标题
DOI：
10.1016/j.conb.2019.02.003
复制
发表时间：
2019-04-01
影响因子：
5.7
通讯作者：
McDermott, Josh H.
中科院分区：
文献类型：
--
作者：
Kell, Alexander J. E.;McDermott, Josh H.
感觉神经科学旨在建立预测神经反应和感知行为的模型，并提供对产生它们的原理的洞察。几十年来，被训练来执行感知任务的人工神经网络作为神经计算的潜在模型引起了人们的兴趣。然而，直到最近，这样的系统才开始在一些现实世界的任务上执行人类的水平。最近深度学习在工程上的成功使人们对人工神经网络作为大脑模型重新产生了兴趣。在这里，我们回顾了深度学习在感觉神经科学中的应用，讨论了潜在的局限性和未来的发展方向。我们强调了深度神经网络的潜在用途，以揭示任务性能如何约束神经系统和行为。特别是，我们考虑任务优化的网络如何以类似于传统理想观察者模型的方式生成关于神经表征和功能组织的假设。
Sensory neuroscience aims to build models that predict neural responses and perceptual behaviors, and that provide insight into the principles that give rise to them. For decades, artificial neural networks trained to perform perceptual tasks have attracted interest as potential models of neural computation. Only recently, however, have such systems begun to perform at human levels on some real-world tasks. The recent engineering successes of deep learning have led to renewed interest in artificial neural networks as models of the brain. Here we review applications of deep learning to sensory neuroscience, discussing potential limitations and future directions. We highlight the potential uses of deep neural networks to reveal how task performance may constrain neural systems and behavior. In particular, we consider how task-optimized networks can generate hypotheses about neural representations and functional organization in ways that are analogous to traditional ideal observer models.