跨皮层层级的实时高效反向投影学习
Learning efficient backprojections across cortical hierarchies in real time
AI总结：
针对皮层学习模型的信用分配问题，提出符合生物合理性的无相位对齐学习PAL方法，利用天然噪声、局部信息和持续可塑性实现多层高效误差传播，在分类任务上性能优于随机突触反馈方法。
摘要：
皮层中的感觉处理与学习模型需要高效地为所有区域的突触分配信用。在深度学习中，一种已知的解决方案是误差反向传播，但该方法需要从前馈路径到反馈路径的权重传输，这在生物学上是不合理的。\n 我们提出了无相位对齐学习（Phaseless Alignment Learning，PAL），这是一种符合生物学合理性的方法，可在分层皮层层级结构中学习高效的反馈权重。该方法通过利用生物物理系统中天然存在的噪声作为额外的信息载体来实现这一目标。在我们的动力学系统中，所有权重通过持续开启的可塑性同时学习，且仅使用突触局部可获取的信息。我们的方法完全无相位（不存在前向和反向传播，也无分阶段学习），能够在多层皮层层级结构中实现高效的误差传播，同时保持符合生物学合理性的信号传输与学习机制。\n 我们的方法适用于广泛的模型类别，并且优于此前已知的符合生物学合理性的信用分配方法：与随机突触反馈相比，它能用更少的神经元解决复杂任务，并学习到更有用的潜在表征。我们使用具有预测编码的皮层微回路模型，在多种分类任务上验证了这一点。
英文摘要：
Models of sensory processing and learning in the cortex need to efficiently assign credit to synapses in all areas. In deep learning, a known solution is error backpropagation, which however requires biologically implausible weight transport from feed-forward to feedback paths. We introduce Phaseless Alignment Learning (PAL), a bio-plausible method to learn efficient feedback weights in layered cortical hierarchies. This is achieved by exploiting the noise naturally found in biophysical systems as an additional carrier of information. In our dynamical system, all weights are learned simultaneously with always-on plasticity and using only information locally available to the synapses. Our method is completely phase-free (no forward and backward passes or phased learning) and allows for efficient error propagation across multi-layer cortical hierarchies, while maintaining biologically plausible signal transport and learning. Our method is applicable to a wide class of models and improves on previously known biologically plausible ways of credit assignment: compared to random synaptic feedback, it can solve complex tasks with less neurons and learn more useful latent representations. We demonstrate this on various classification tasks using a cortical microcircuit model with prospective coding.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
