JPC用JAX实现预测编码网络的灵活训练，提升推理速度与效率。
JPC: Flexible Inference for Predictive Coding Networks in JAX
- 采用微分方程求解器替代传统欧拉积分，优化预测编码网络的推理动态
- 二阶求解器比标准方法提速显著，且在多种任务和网络深度下性能相当
- 提供理论工具支持研究，适合神经网络建模与认知计算方向学者使用
我们提出JPC，一个基于JAX的预测编码网络（PCN）训练库。JPC提供了简单、快速且灵活的接口，可训练判别式、生成式及混合型PCN。不同于现有工具，JPC利用常微分方程求解器来整合PCN的梯度流推理动态。实验发现，二阶求解器相比标准欧拉积分显著提升运行速度，同时在多种任务与网络深度下保持相近性能。JPC还包含若干理论分析工具，助力未来对预测编码网络的研究。代码已开源于https://github.com/thebuckleylab/jpc。
原文摘要 · Abstract (English)
We introduce JPC, a JAX library for training neural networks with Predictive Coding. JPC provides a simple, fast and flexible interface to train a variety of PC networks (PCNs) including discriminative, generative and hybrid models. Unlike existing libraries, JPC leverages ordinary differential equation solvers to integrate the gradient flow inference dynamics of PCNs. We find that a second-order solver achieves significantly faster runtimes compared to standard Euler integration, with comparable performance on a range of tasks and network depths. JPC also provides some theoretical tools that can be used to study PCNs. We hope that JPC will facilitate future research of PC. The code is available at https://github.com/thebuckleylab/jpc.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。