PulseAugur
中
实时 13:00:43

CNet框架通过Wirtinger导数实现复杂值深度学习

研究人员开发了CNet,一个用于训练深度复杂值神经网络(CVNN)和使用Wirtinger导数优化复杂值函数的C++/CUDA框架。该框架采用物理原生方法,将神经网络视为复杂运算的级联,并将分类视为玻恩规则测量。CNet包含其层的CPU参考和CUDA内核,计算图跨批次克隆以进行GPU执行。该框架还集成了可学习的复杂卷积网络的信号处理原语和一个具有低内存推理模式的真实Adam优化器。初步研究表明,使用CNet构建的复杂值、FNet风格的因果序列模型在字符级语言建模方面,其性能与实值模型相当或超越,并且在不到一半的训练时间内达到了收敛质量。 AI

影响 该框架可能为信号处理和物理学等领域的复杂数据建模带来新方法。

排序理由 该集群描述了一个用于复杂值深度学习的新框架和相关研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

CNet框架通过Wirtinger导数实现复杂值深度学习

本文如何被排名

Signal score
7 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一个用于复杂值深度学习的新框架和相关研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Marcel Crasmaru ·

    CNet:一种具有Wirtinger自动微分和FFT-Hadamard卷积的复值深度学习框架

    arXiv:2610.08592v1 Announce Type: new Abstract: CNet is a C++/CUDA framework for building and training deep complex-valued neural networks (CVNNs) and, more generally, for optimizing complex-valued functions by gradient descent with Wirtinger (CR-calculus) derivatives. It takes a…