神经网络 乳腺癌数据集的神经网络，可产生概率并对新患者进行分类。 训练数据 该模型是使用699例乳腺癌患者的数据集构建的。 数据集经过归一化和清洗，最终使500名患者接受了培训和测试的最终数据集。 共有500例患者，其中262例（52.4％）患有良性肿瘤，238例（47.6％）患有恶性肿瘤。 为了进行训练，使用了80％的数据，其中40％是良性肿瘤，40％是恶性肿瘤，其余20％用于测试。 在这20％中，12.4％来自良性肿瘤，而7.6％来自恶性肿瘤。 怎么跑 克隆存储库 启动你的服务器 现在，您可以访问神经网络预测的结果并查看模型训练的性能图。 内容

《Neural Networks for Time Series Forecasting with R》，2017年新出书籍，深度学习用于时间序列

《TF-GNN：Graph Neural Networks》附录《A.2.2 Creating GraphTensors》例程

吴恩达机器学习 Neural Networks for Binary Classification Jupyter note版本编程作业 机器学习与数据挖掘

Neural Networks for Handwritten Digit Recogn 吴恩达机器学习 jupyter note 版本编程作业 机器学习与数据挖掘 用神经网络识别手写数字0-9

Michael Nielsen的Neural Networks and Deep Learning，由Xiaohu Zhu，Freeman Zhang等人提供中文翻译的开源版本，这个是最新的v0.5中文版。

In this paper we propose acoustic direction of arrival (DOA) estimation with neural networks. Conventional signal processing tasks such as DOA estimation have benefited from recent advancements in deep learning, which leads to a data-driven approach that allows neural networks to be employed in a black-box manner. From traditional aspects, modern network models often lack interpretability when directly employed in signal processing realm. As an alternative, we introduce a learnable network from

神经网络和深度学习（Neural Networks and Deep Learning） Michael Nielsen 中文版

Most 3D shape classification and retrieval algorithms were based on rigid 3D shapes, deploying these algorithms directly to nonrigid 3D shapes may lead to poor performance due to complexity and changeability of non-rigid 3D shapes. To address this challenge, we propose a fusion view convolutional neural networks (FVCNN) framework to extract the deep fusion features for non-rigid 3D shape classification and retrieval. We first propose a projection module to transform the nonrigid 3D shape into a

Neural Networks and Deep Learning神经网络与深度学习 中文版.pdf 个人收集电子书，仅用学习使用，不可用于商业用途，如有版权问题，请联系删除！