|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/from-0-to-1-tensorflow-for-deep-learning/
课程评论：没有评论
课程名称：TensorFlow与Google Cloud ML引擎的深度学习 课程概述： 本课程深入讲解TensorFlow（TF）及其在深度学习中的应用，TF因其简单性和强大的功能迅速成为构建复杂神经网络的首选技术。Google Cloud Platform为TF模型的规模化运行和分布式训练及预测提供了极佳的环境。本课程为全面的基础教程，无需任何TensorFlow背景知识，只需具备基本的Python编程能力。 课程内容： 1. 深度学习基础： - 神经元的概念 - 神经网络如何连接神经元以“学习”复杂的函数 - 如何利用TF轻松构建神经网络模型 2. 深度学习在著名机器学习问题中的应用： - 回归、分类、聚类与自编码 3. 卷积神经网络（CNNs）： - 核函数、特征图 - CNN与深度神经网络（DNN）的比较 4. 循环神经网络（RNNs）： - LSTM、时间反向传播、处理梯度消失/爆炸问题 5. 无监督学习技术： - 自编码、K均值聚类、主成分分析（PCA）作为自编码 6. 图像处理 7. 文档处理与词嵌入 8. Google Cloud ML引擎： - 在云中进行TF模型的分布式训练与预测 - 使用TensorFlow估计器 注：课程大纲未提供具体细节。
TensorFlow is quickly becoming the technology of choice for deep learning, because of how easy TF makes it to build powerful and sophisticated neural networks. The Google Cloud Platform is a great place to run TF models at scale, and perform distributed training and prediction. This is a comprehensive, from-the-basics course on TensorFlow and building neural networks. It assumes no prior knowledge of Tensorflow, all you need to know is basic Python programming. What's covered: Deep learning basics: What a neuron is; how neural networks connect neurons to 'learn' complex functions; how TF makes it easy to build neural network modelsUsing Deep Learning for the famous ML problems: regression, classification, clustering and autoencodingCNNs - Convolutional Neural Networks: Kernel functions, feature maps, CNNs v DNNs RNNs - Recurrent Neural Networks: LSTMs, Back-propagation through time and dealing with vanishing/exploding gradientsUnsupervised learning techniques - Autoencoding, K-means clustering, PCA as autoencoding Working with imagesWorking with documents and word embeddingsGoogle Cloud ML Engine: Distributed training and prediction of TF models on the cloudWorking with TensorFlow estimators
