An important difference between brains and deep neural networks is the way they learn. Nervous systems learn online where a stream of noisy data points are presented in a non-independent, identically distributed (non-i.i.d.) way. Further, synaptic plasticity in the brain depends only on information local to synapses. Deep networks, on the other hand, typically use non-local learning algorithms and are trained in an offline, non-noisy, i.i.d. setting. Understanding how neural networks learn under the same constraints as the brain is an open problem for neuroscience and neuromorphic computing. A standard approach to this problem has yet to be established. In this paper, we propose that discrete graphical models that learn via an online maximum a posteriori learning algorithm could provide such an approach. We implement this kind of model in a novel neural network called the Sparse Quantized Hopfield Network (SQHN). We show that SQHNs outperform state-of-the-art neural networks on associative memory tasks, outperform these models in online, non-i.i.d. settings, learn efficiently with noisy inputs, and are better than baselines on a novel episodic memory task.

翻译：大脑与深度神经网络之间的一个重要差异在于它们的学习方式。神经系统通过在线学习，即在非独立同分布（non-i.i.d.）条件下处理一连串带有噪声的数据点。此外，大脑中的突触可塑性仅依赖于突触局部的信息。而深度神经网络通常采用非局域学习算法，并在离线、无噪声的独立同分布（i.i.d.）环境中训练。理解神经网络如何在大脑的相同约束条件下进行学习，至今仍是神经科学和神经形态计算领域的一个开放性问题。目前尚未建立处理该问题的标准方法。在本文中，我们提出通过在线最大后验学习算法进行学习的离散图模型或可提供此类方法。我们在一类名为稀疏量化Hopfield网络（Sparse Quantized Hopfield Network, SQHN）的新型神经网络中实现了该模型。研究表明，SQHN在联想记忆任务上优于最先进的神经网络，在在线非独立同分布环境中表现更佳，能高效处理含噪声输入，并在新型情景记忆任务中优于基线模型。