预训练与压缩小模型谁更可信？IJCNN权威基准测试给出对比答案。
arXiv:2608.11981v1 Announce Type: new Abstract: Small Language Models (SLMs) have emerged as a more efficient alternative to traditional Large Languag…
新文档带你用CNN训练MNIST手写数字分类，实操指南清晰易懂。
#611 — July 24, 2026 Read the Web Version Go Weekly GoMLX: Accelerated Machine Learning Framework for Go — A Python-free, idiomatically Go alternativ…
轻量级CNN+Mamba框架精准自动睡眠分期，专攻小样本EEG数据集，高效实用。
arXiv:2607.04934v1 Announce Type: new Abstract: Automatic sleep staging is a key technology for precise diagnosis and treatment of sleep disorders as …
CNN上采样麦克风阵列协方差矩阵，声学成像迎来新思路，音频处理与深度学习的硬核碰撞
arXiv:2607.01295v1 Announce Type: cross Abstract: Acoustic imaging visualization is a core methodology in acoustics, enabling spatial analysis of soun…
利用CNN训练中的不确定性作为数据增强新策略，为提升模型泛化能力提供创新思路。
arXiv:2509.05238v2 Announce Type: replace-cross Abstract: Deep learning (DL) has transformed neuroimaging by delivering state-of-the-art performance w…
基于MSDF数字串行算术的FPGA方案，在CNN加速中实现高能效与低资源占用，边缘计算场景的实用新思路。
arXiv:2606.25562v1 Announce Type: cross Abstract: This paper presents an energy-efficient hardware acceleration of the convolutional layers in the U-N…
双分支CNN-Transformer架构，精准预测脑肿瘤浸润风险，医疗AI新突破。
arXiv:2605.02230v2 Announce Type: replace-cross Abstract: Gliomas are aggressive brain tumors that infiltrate surrounding tissue beyond the visible tu…
地理基础模型与CNN混合架构，为滑坡检测提供全新辅助上下文，精度提升显著。
arXiv:2606.14081v1 Announce Type: cross Abstract: Rapid post-event landslide mapping is essential for disaster response but remains difficult to autom…
重尾分布下的扩散模型新突破：自调节退火机制，无需手动调参即可优化生成质量。
arXiv:2606.01645v1 Announce Type: cross Abstract: Diffusion models have emerged as a leading framework for deep generative modeling. While the standar…
CNN起诉Perplexity AI，指控其未经授权抓取并复制新闻内容，AI版权争议再掀波澜。
Article URL: https://www.cnn.com/2026/05/28/media/cnn-sues-perplexity-ai-copyright Comments URL: https://news.ycombinator.com/item?id=48308614 Points:…
提出一种提升输入凸神经网络训练效率的新方法，适用于密度估计与标准化流。
arXiv:2605.24274v1 Announce Type: new Abstract: Input-convex neural networks (ICNNs) are widely used for log-concave density estimation, convex-potent…
轻量级CNN模型在边缘网络实现高效DDoS攻击检测，专为资源受限场景优化，兼顾速度与准确率
arXiv:2309.05646v2 Announce Type: replace-cross Abstract: Distributed Denial of Service (DDoS) attacks remain a persistent threat to the availability …
提出FM-G-CAM新方法，全面解释CNN预测，提升可解释AI在视觉领域的实用性。
arXiv:2312.05975v3 Announce Type: replace-cross Abstract: Explainability is a vital aspect of modern AI for real-world impact and usability. The main …