创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

Deepity 0.1.0a3 发布预测编码引擎

AI 总结

独立开发者发布 Deepity 0.1.0a3,这是一款开源预测编码库,采用 C++20 核心、手写 CPU SIMD 内核,并提供以 pydeepity 名义发布在 PyPI 上的 Python 绑定。作者在配置一致的 MNIST 测试中报告,Deepity 用 487.5 秒达到 98.21% 准确率,jpc 为 97.55%,ngc-learn 为 98%。测试在搭载第 12 代 Intel Core i7-12700H 的笔记本电脑 CPU 上进行,原始日志随代码仓库提供。当前 alpha 版 CUDA 后端可以构建和运行,但大规模 ImageNet 训练仍在优化中,尚未开放,且作者没有公布 CPU 与 CUDA 的对比数据。

深度见解

此次发布让外界可以查看并试用一款采用内核级 CPU 优化的开源预测编码实现。

I've been building a predictive coding (PC) engine from scratch in C++20, with a thin Python layer on top, and just cut the first public release. Posting here for feedback and because I haven't seen many from-scratch PC implementations with real kernel-level optimization work behind them.

What predictive coding is: instead of backprop's single global error signal flowing backward through a stored computation graph, each layer in a PCN holds a local belief about its own state and compares it against a top-down prediction from the layer above. Training alternates between "settling" (every layer locally reduces its own prediction error over several steps) and a weight update that only looks at that layer's own error. No layer needs the transpose of another layer's weights, and there's no backward graph to keep in memory.

What Deepity actually is:

- A C++20 core with hand-written AVX2/AVX-512 SIMD kernels (via SLEEF for the transcendental activations), OpenBLAS/MKL for GEMM, and a CUDA backend (cuBLAS + CUTLASS + CUDA graph capture for the settling loop) that's still being tuned for large-scale training (not available yet).

#Deepity 0.1.0a3#pydeepity#jpc#ngc-learn#PyTorch#CUDA#OpenBLAS#Intel MKL#SLEEF#nanobind

原文约 3 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。