Predictive Coding, Variational Autoencoders, and Biological Connections

Tightening the Biological Constraints on Gradient-Based Predictive Coding

Predictive coding (PC) is a general theory of cortical function. The local, gradient-based learning rules found in one kind of PC model have recently been shown to closely approximate backpropagation. This finding suggests that this gradient-based PC model may be useful for understanding how the brain solves the credit assignment problem. The model may also be useful for developing local learning algorithms that are compatible with neuromorphic hardware. In this paper, we modify this PC model so that it better fits biological constraints, including the constraints that neurons can only have po…

Unary Coding for Neural Network Learning

This paper presents some properties of unary coding of significance for biological learning and instantaneously trained neural networks.

关于预测编码与反向传播之间的关系

On the relationship between predictive coding and backpropagation

本文回顾并扩展了在监督学习任务中训练前馈人工神经网络时预测编码与反向传播之间数学关系的研究，并提供了Torch2PC函数库以支持在PyTorch模型中执行预测编码。

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

Bayesian optimization (BayesOpt) is a gold standard for query-efficient continuous optimization. However, its adoption for drug design has been hindered by the discrete, high-dimensional nature of the decision variables. We develop a new approach (LaMBO) which jointly trains a denoising autoencoder with a discriminative multi-task Gaussian process head, allowing gradient-based optimization of multi-objective acquisition functions in the latent space of the autoencoder. These acquisition functions allow LaMBO to balance the explore-exploit tradeoff over multiple design rounds, and to balance ob…

基于预测编码的局部赫布学习的脉冲神经网络：PC-SNN

PC-SNN: Predictive Coding-based Local Hebbian Plasticity Learning in Spiking Neural Networks

PC-SNN通过整合预测编码与脉冲神经网络，实现生物合理的局部赫布学习，无需反向传播，提升SNN训练的可扩展性和生物合理性。

Efficient Online Learning with Predictive Coding Networks: Exploiting Temporal Correlations

Robotic systems operating at the edge require efficient online learning algorithms that can continuously adapt to changing environments while processing streaming sensory data. Traditional backpropagation, while effective, conflicts with biological plausibility principles and may be suboptimal for continuous adaptation scenarios. The Predictive Coding (PC) framework offers a biologically plausible alternative with local, Hebbian-like update rules, making it suitable for neuromorphic hardware implementation. However, PC's main limitation is its computational overhead due to multiple inference i…