预测前向前前进的算法 (The Predictive Forward-Forward Algorithm)

from arxiv, Revisions, version now incudes PFF's learnable lateral self-excitation and cross-inhibitory synapses, additional experimental results, discussion of computational benefits/self-generated negative samples, and an expanded appendix

We propose the predictive forward-forward (PFF) algorithm for conducting credit assignment in neural systems. Specifically, we design a novel, dynamic recurrent neural system that learns a directed generative circuit jointly and simultaneously with a representation circuit, integrating learnable lateral competition and elements of predictive coding, an emerging and viable neurobiological process theory of cortical function, with the forward-forward (FF) adaptation scheme. Furthermore, PFF efficiently learns to propagate learning signals and updates synapses with forward passes only, eliminating key structural and computational constraints imposed by a backpropagation-based scheme. Besides computational advantages, the PFF process could prove useful for understanding the learning mechanisms behind biological neurons that use local signals despite missing feedback connections. We run experiments on image data and demonstrate that the PFF procedure works as well as backpropagation of errors, offering a promising brain-inspired learning algorithm for classifying, reconstructing, and synthesizing data patterns.

翻译：我们提出了在神经系统中进行信用分配的预测前向算法(PFF) 。具体地说,我们设计了一个新颖的、动态的经常性神经系统,与代表电路同时并肩学习定向基因电路,将可学习的横向竞争和预测编码要素、新出现和可行的神经生物过程功能循环理论与前向(FF)适应计划结合起来。此外,PFF有效地学会了传播学习信号和仅以前向传递更新突触,消除了基于后向再分析计划的关键结构和计算限制。除了计算优势外,PFF过程可以证明有助于理解尽管缺少反馈连接但使用当地信号的生物神经元背后的学习机制。我们在图像数据上进行实验,并证明PFF程序既对错误进行反向分析,也为分类、重建和合成数据模式提供了充满希望的由大脑启发的学习算法。