深度学习综述讨论简介deepLearning.pptxVIP

;Outline;Deep Learning(Hinton,2006);Development History;Deep Learning Frameworks;Deep neural network architectures;DBN(Deep Belief Network,2006);RNN(Recurrent Neural Network,2013);GANs(Generative Adversarial Networks,2014);Long Short-Term Memory(LSTM,1997);Neural Networks;Convolutional Neural Networks(CNN);Convolution layer;Pooling layer;Fully connected layer and Softmax layer;Training and Testing;CNN Structure Evolution;LeNet(LeCun,1998);AlexNet(Alex,2012);Overfeat(2013);VGG-Net(Oxford University,2014);Network-in-Network(NIN, Shuicheng Yan, 2013);GoogLeNet(Inception V1,2014);Inception V2(2015);Inception V3(2015);ResNet(Kaiwen He, 2015);FractalNet;Inception V4(2015);Inception-ResNet;Comparison;SqueezeNet?;Xception;R-CNN(2014);SPP-Net(Spatial pyramid pooling network,2015);Fast R-CNN(2015);Faster R-CNN(2015);Training tricks;Data Augmentation;Dropout(2012);ReLU(Rectified Linear Unit);Batch Normalization(2015);Application in Aesthetic Image Evaluation;Photo Quality Assessment with DCNN that Understands Image Well;Rating image aesthetics using deep learning;A multi-scene deep learning model for image aesthetic evaluation;Example -Load the dataset;Example –Model;Example –Train and Test;Example –Result;References;