The 1th chapter introduces the course of deep learning, mainly introduces the application category of deep learning, the demand of talents and the main algorithms. This paper introduces the course chapters, the course arrangement, the applicable crowd, the prerequisites and the degree to be achieved after the completion of the study, so that students have a basic understanding of the course. The 2nd chapter of Neural Network Introductory course of this practical course. This paper introduces the introduction of machine learning and deep learning, and illustrates the latest progress of deep learning through several projects. The basic knowledge of this course is comprehensively explained by explaining the basic structure of neural network, neuron and its extended logistic regression model, including neuron, activation function, objective function, gradient descent, learning rate, TensorFlow Foundation and TensorFlow Code implementation of the model. ... 3rd convolution Neural Network This course is a total of two parts, the first part of the neural network is a complete introduction, including neural network structure, forward propagation, reverse propagation, gradient descent and so on. The second part explains the basic structure of convolutional neural network, including convolution, pooling and full connection. In particular, it focuses on the details of convolution operation, including convolution core structure, convolution calculation, calculation of convolution kernel parameters, and introduces a basic convolutional neural network structure. ... the 4th chapter of convolutional Neural Network Advanced This section explains the structure of high-level convolutional neural networks, including Alexnet, Vggnet, ResNet, Inceptionnet, Mobilenet, and their evolution. For each structure, this course explains the problems it solves, the basic ideas of substructure, and the important techniques used in the model. After completing this course, students can achieve the ability to build different types of convolutional neural networks flexibly. ... the 5th chapter of convolutional Neural Network Assistant This section summarizes and sums up the Common assistant skills ("Alchemy") in convolutional networks. The principle behind some important assistant technique is explained. The assistant techniques include gradient descent, learning rate, activation function, initialization of network parameters, batch normalization, data enhancement, visual training process analysis, fine-tune, and many other network tuning techniques. After completing this course, students can call themselves "alchemist". ... the 6th chapter of image style conversion This course is an application course of convolutional neural Network, which uses a pre-trained Vgg model to realize the image style conversion algorithm. The knowledge points of this course include the use of convolutional neural networks to extract features, the definition of content features and stylistic features, and image reconstruction methods. In addition to the basic image style conversion algorithm, this course further introduces two other improved style conversion algorithms. ... the 7th chapter of Cyclic Neural network is explained in this course. Including recurrent neural network to solve the sequence problem and the basic structure of the network, multi-layer, bidirectional, residual structure and recursive truncationGradient drop and so on. The emphasis on the common variant-long-term memory network is detailed. This paper explains and contrasts the various application models of cyclic neural network and convolutional neural network in text classification, including TEXTRNN, Textcnn and Han (level attention network, introducing attention mechanism) and so on. ... the 8th chapter of image Generation This course is a combined application of convolutional neural networks and recurrent neural networks. This course explains several model variants, including multi-modal RNN, show and tell, show attend and tell, and more. At the end of the course, the text generation image of inverse problem is described, and the anti-neural network is introduced. After learning 567 courses, students should have a deep understanding of the application of convolutional neural networks and recurrent neural networks. ... the 9th chapter of the Anti-neural network This course is an explanation of the latest progress in deep learning--the anti-neural network. It mainly includes the idea of resisting the neural network and two specific Gan networks, the deep convolution countermeasure Generation Network (Dcgan) and the image translation (PIX2PIX) model. The knowledge points involved include generator G, discriminant D, deconvolution, u-net and so on. ... 10th Automatic Machine Learning Network-AUTOML This course provides an explanation of the latest advances in deep learning-automated machine learning networks. Automatic machine learning uses recurrent neural networks to automatically search for the network structure parameters that need to be adjusted, resulting in better results than human "alchemist". In this course, three kinds of new automatic machine learning algorithms are explained, and three kinds of algorithms are sequentially progressive, which automatically search for the optimal convolution neural network structure in the field of image classification. ... the 11th chapter of the course summarizes the overall curriculum review : Baidu Network disk download
Deep Learning Neural Network (Cnn/rnn/gan) algorithm principle + actual combat
