|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/fundamentals-in-neural-networks/
课程评论：没有评论
课程名称：神经网络基础 课程概述： 深度学习（也称为深度结构学习）是基于人工神经网络和表示学习的一种机器学习方法。学习可以是监督的、半监督的或无监督的。深度学习架构如深度神经网络、深度信念网络、深度强化学习、递归神经网络和卷积神经网络已被广泛应用于多个领域，包括计算机视觉、语音识别、自然语言处理、机器翻译、生物信息学、药物设计、医学图像分析、材料检测和棋类程序等，取得的成果在某些方面超过了人类专家的表现。 本课程共分为三个主要部分： 1. 神经网络 2. 卷积神经网络 3. 递归神经网络 你将获得大约4小时的学习材料，内容包括详细的讨论、数学描述和三种常见神经网络的代码演示。 课程具体内容： - 第1部分：神经网络 - 线性回归 - 逻辑回归 - 神经网络的目的 - 前向传播 - 反向传播 - 激活函数（Relu、Sigmoid、Softmax） - 交叉熵损失函数 - 梯度下降 - 第2部分：卷积神经网络 - 图像数据 - 张量与矩阵 - 卷积运算 - 填充 - 步幅 - 2D和3D卷积 - VGG16 - 残差网络 - 第3部分：递归神经网络 - 欢迎 - 为什么使用RNN - 语言处理 - RNN中的前向传播 - 时间反向传播 - 门控递归单元（GRU） - 长短期记忆（LSTM） - 双向RNN（bi-RNN） - 技术演练：人工神经网络 本节逐步演示使用TensorFlow部署人工神经网络的每一个构建块。 - 技术演练：卷积神经网络 本节逐步演示使用TensorFlow部署卷积神经网络的每一个构建块。 - 技术演练：递归神经网络 本节逐步演示使用TensorFlow部署递归神经网络的每一个构建块。 - 高级主题：自编码器 本节逐步演示使用TensorFlow部署自编码器的每一个构建块，并探讨使用自编码器的潜在层解决推断问题。 - 高级主题：图像分割 本节逐步演示使用TensorFlow部署图像到图像模型的每一个构建块。 本课程旨在为学员提供深入的神经网络知识及其在实际中的应用，使他们能够设计和实现最新的深度学习模型。
Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised. Deep-learning architectures such as deep neural networks, deep belief networks, deep reinforcement learning, recurrent neural networks and convolutional neural networks have been applied to fields including computer vision, speech recognition, natural language processing, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance.This course covers the following three sections: (1) Neural Networks, (2) Convolutional Neural Networks, and (3) Recurrent Neural Networks. You will be receiving around 4 hours of materials on detailed discussion, mathematical description, and code walkthroughs of the three common families of neural networks. The descriptions of each section is summarized below.Section 1 - Neural Network1.1 Linear Regression1.2 Logistic Regression1.3 Purpose of Neural Network1.4 Forward Propagation1.5 Backward Propagation1.6 Activation Function (Relu, Sigmoid, Softmax)1.7 Cross-entropy Loss Function1.8 Gradient DescentSection 2 - Convolutional Neural Network2.1 Image Data2.2 Tensor and Matrix2.3 Convolutional Operation2.4 Padding2.5 Stride2.6 Convolution in 2D and 3D2.7 VGG162.8 Residual NetworkSection 3 - Recurrent Neural Network3.1 Welcome3.2 Why use RNN3.3 Language Processing3.4 Forward Propagation in RNN3.5 Backpropagation through Time3.6 Gated Recurrent Unit (GRU)3.7 Long Short Term Memory (LSTM)3.8 Bidirectional RNN (bi-RNN)Section 4 - Technical Walkthrough: Artificial Neural NetworkThis section walks through each and every building block of deploying an Artificial Neural Network using tensorflow.Section 5 - Technical Walkthrough: Convolutional Neural NetworkThis section walks through each and every building block of deploying a Convolutional Neural Network using tensorflow.Section 6 - Technical Walkthrough: Recurrent Neural NetworkThis section walks through each and every building block of deploying an Recurrent Neural Network using tensorflow.Section 7 - Advanced Topics: AutoencodersThis section walks through each and every building block of deploying an Autoencoder using tensorflow. Further, we explore the inference problems using the latent layers of the autoencoder.Section 8 - Advanced Topics: Image SegmentationThis section walks through each and every building block of deploying an Image-to-image model using tensorflow.
