Curl Descent: Non-Gradient Learning Dynamics with Sign-Diverse Plasticity
Département d’Études Cognitives(认知研究系);Edmond and Lily Safra Center for Brain Sciences(埃德蒙与莉莉·萨弗脑科学中心);École normale supérieure - PSL(巴黎高等师范学院-PSL);The Hebrew University of Jerusalem(耶路撒冷希伯来大学)
Gradient-based algorithms are a cornerstone of artificial neural network training, yet it remains unclear whether biological neural networks use similar gradient-based strategies during learning. Experiments often discover a diversity of synaptic plasticity rules, but whether these amount to an approximation to gradient descent is unclear. Here we investigate a previously overlooked possibility: that learning dynamics may include fundamentally non-gradient "curl"-like components while still being able to effectively optimize a loss function. Curl terms naturally emerge in networks with inhibitory-excitatory connectivity or Hebbian/anti-Hebbian plasticity, resulting in learning dynamics that cannot be framed as gradient descent on any objective. To investigate the impact of these curl terms, we analyze feedforward networks within an analytically tractable student-teacher framework, systematically introducing non-gradient dynamics through neurons exhibiting rule-flipped plasticity. Small curl terms preserve the stability of the original solution manifold, resulting in learning dynamics similar to gradient descent. Beyond a critical value, strong curl terms destabilize the solution manifold. Depending on the network architecture, this loss of stability can lead to chaotic learning dynamics that destroy performance. In other cases, the curl terms can counterintuitively speed learning compared to gradient descent by allowing the weight dynamics to escape saddles by temporarily ascending the loss. Our results identify specific architectures capable of supporting robust learning via diverse learning rules, providing an important counterpoint to normative theories of gradient-based learning in neural networks.
Isomorphic Functionalities between Ant Colony and Ensemble Learning: Part III -- Gradient Descent, Neural Plasticity, and the Emergence of Deep Intelligence
School of Mathematics and Statistics, Rochester Institute of Technology(罗彻斯特理工学院数学与统计学院);Gosnell School of Life Sciences, Rochester Institute of Technology(罗彻斯特理工学院戈斯内尔生命科学学院);Center for Imaging Science, Rochester Institute of Technology(罗彻斯特理工学院成像科学中心)
Training Spiking Neural Networks Using Lessons From Deep Learning
UC Santa Cruz(加州大学圣克鲁兹分校);University of Michigan(密歇根大学);UWA(西澳大学);Harvard University(哈佛大学);Forschungszentrum Jülich(于利希研究中心);RWTH Aachen(亚琛工业大学);SynSense(SynSense(类脑智能公司));Hanyang University(汉阳大学)
The Swiss AI Lab IDSIA(瑞士人工智能实验室IDSIA);University of Lugano (USI)(卢加诺大学);SUPSI(瑞士意大利语区高等专业学院);King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学)
Meta-Reinforcement Learning with Self-Modifying Networks
Artificial and Natural Intelligence Toulouse Institute(图卢兹人工智能与自然智能研究所);Universite de Toulouse(图卢兹大学);Carney Institute for Brain Science(卡尼脑科学研究所);Brown University(布朗大学);Centre de Recherche Cerveau & Cognition(大脑与认知研究中心);CNRS(法国国家科学研究中心)