论文标题
以生物学启发的神经元适应改善了神经网络的学习
Biologically-inspired neuronal adaptation improves learning in neural networks
论文作者
论文摘要
由于人类在许多任务上仍然超过人工神经网络，因此从大脑中汲取灵感可能有助于改善当前的机器学习算法。对比性HEBBIAN学习（CHL）和平衡传播（EP）是生物学上合理的算法，仅使用局部信息（不明确计算梯度）更新权重，并且仍然可以实现与常规背部相当的性能。在这项研究中，我们以调整后的适应性增强了CHL和EP，这是受到神经元观察到的适应效应的启发，其中神经元在短时间后调整了神经元对给定刺激的反应。我们将此适应性功能添加到多层感知器和接受MNIST和CIFAR-10培训的卷积神经网络中。令人惊讶的是，适应性改善了这些网络的性能。我们讨论了这一想法的生物学灵感，并研究了为什么神经元适应可能是提高学习稳定性和准确性的重要大脑机制。
Since humans still outperform artificial neural networks on many tasks, drawing inspiration from the brain may help to improve current machine learning algorithms. Contrastive Hebbian Learning (CHL) and Equilibrium Propagation (EP) are biologically plausible algorithms that update weights using only local information (without explicitly calculating gradients) and still achieve performance comparable to conventional backpropagation. In this study, we augmented CHL and EP with Adjusted Adaptation, inspired by the adaptation effect observed in neurons, in which a neuron's response to a given stimulus is adjusted after a short time. We add this adaptation feature to multilayer perceptrons and convolutional neural networks trained on MNIST and CIFAR-10. Surprisingly, adaptation improved the performance of these networks. We discuss the biological inspiration for this idea and investigate why Neuronal Adaptation could be an important brain mechanism to improve the stability and accuracy of learning.
