Laboratoire de Neurosciences Cognitives et Computationnelles, Institut National de la Santé et de la Recherche Médicale (Inserm), Paris, France.
Département des Neurosciences Fondamentales, Université de Genève, Geneva, Switzerland.
Sci Adv. 2024 Nov;10(44):eadl3931. doi: 10.1126/sciadv.adl3931. Epub 2024 Oct 30.
Random noise in information processing systems is widely seen as detrimental to function. But despite the large trial-to-trial variability of neural activity, humans show a remarkable adaptability to conditions with uncertainty during goal-directed behavior. The origin of this cognitive ability, constitutive of general intelligence, remains elusive. Here, we show that moderate levels of computation noise in artificial neural networks promote zero-shot generalization for decision-making under uncertainty. Unlike networks featuring noise-free computations, but like human participants tested on similar decision problems (ranging from probabilistic reasoning to reversal learning), noisy networks exhibit behavioral hallmarks of optimal inference in uncertain conditions entirely unseen during training. Computation noise enables this cognitive ability jointly through "structural" regularization of network weights during training and "functional" regularization by shaping the stochastic dynamics of network activity after training. Together, these findings indicate that human cognition may ride on neural variability to support adaptive decisions under uncertainty without extensive experience or engineered sophistication.
信息处理系统中的随机噪声通常被认为对功能有害。但是，尽管神经活动在很大程度上存在试验间的可变性，但人类在目标导向行为中表现出对不确定条件的惊人适应能力。构成一般智力的这种认知能力的起源仍然难以捉摸。在这里，我们表明，人工神经网络中的适度计算噪声可促进在不确定条件下进行决策的零样本泛化。与具有无噪声计算的网络不同，但与在类似决策问题上接受测试的人类参与者（从概率推理到反转学习）相似，嘈杂的网络表现出在训练期间完全看不到的不确定条件下进行最佳推理的行为特征。计算噪声通过在训练过程中对网络权重进行“结构”正则化以及通过训练后塑造网络活动的随机动力学来进行“功能”正则化，从而共同实现这种认知能力。这些发现表明，人类认知可能依赖于神经变异性来支持不确定条件下的适应性决策，而无需广泛的经验或工程复杂性。
