深度学习综述讨论简介deepLearningPPT课件.pptxVIP

Introduction to Deep LearningHuihui LiuMar.1, 20171 OutlineConception of deep learningDevelopment historyDeep learning frameworksDeep neural network architecturesConvolutional neural networks Introduction Network structure Training tricksApplication in Aesthetic Image EvaluationIdea 2 Deep Learning(Hinton,2006)Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high level abstractions in data. The advantage of deep learning is to extracting features automatically instead of extracting features manually.Computer visionSpeech recognitionNatural language processing3 Development Histor 1950 1960 1970 1980 1990 2000 2010 MP model1958Single- layerPerceptron1969XORproblem1986BP algorithm1989CNN-LeNeVMLSTMGradient disappearance probleBNReLU201120122015DropoutAlexNetBNFaster R-CNNResidualNetGeoffrey HintonW.S.McCullochW.PittsRosenblattMarvin MinskyYann LeCunHintonHintonHintonLeCunBengio4 Deep Learning Frameworks5 Deep neural network architecturesDeep Belief Networks(DBN)Recurrent Neural Networks (RNN)Generative Adversarial Networks (GANs)Convolutional Neural Networks (CNN)Long Short-Term Memory(LSTM)6 DBN(Deep Belief Network,2006)Hidden units and visible units Each unit is binary(0 or 1). Every visible unit connects to all the hidden units. Every hidden unit connects to all the visible units. There are no connections between v-v and h-h.Hinton G E. Deep belief networks[J]. Scholarpedia, 2009, 4(6):5947.Fig1. RBM(restricted Boltzmann machine) structure.Fig2. DBN(deep belief network) structure.Idea ? Composed of multiple layers of RBM.How to we train these additional layers? Unsupervised greedy approach7 RNN(Recurrent Neural Network,2013)What? RNN aims to process the sequence data. RNN will remember the previous information and apply it to the calculation of the