机器学习与深度学习解读.pptxVIP

机器学习与深度学习解读 人工智能与机器学习深度学习与深度强化学习产业应用实践 大数据与AI未来趋势分析区块链赋权模型算法互联网云计算物联网大数据 AlphaGo: Techniques & Applications What is AI？"An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through effectors"- Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Novig 计算思维、推理思维 Computer Vision: Car detectionTesting:What is this? Not a carCars Seeing with your tongueHuman echolocation (sonar)Haptic belt: Direction senseImplanting a 3rd eyeSensor representations in the brain[BrainPort; Welsh & Blasch, 1997; Nagel et al., 2005; Constantine-Paton & Law, 2009] 从大数据到人工智能 10NLTKTheano大数据 +深度学习 人工智能与机器学习深度学习与深度强化学习产业应用实践 What is deep learningA set of machine learning techniques that can learn useful representations of features directly from images, text and sound.AchievementsImageNetGoogle Neural Machine TranslationAlphaGo/AlphaZeroBenefit from big data and GPU A typical Deep Learning workflowLoad dataSelect neural network architecture, optimize the parameters Build your own deep learning modelModelImages(#)Classes(#)ImageNet14M20KSkin cancer129,450757 Transfer Learning PipelinePre-trained CNN modelSoftmax classification (Trainable parameters)Load data as DataFrame OutlineWhat is Deep Reinforcement Learning?Deep Learning IntroductionReinforcement Learning IntroductionAdvanced Deep Reinforcement Learning 1. What is the deep reinforcement learning？Deep?? =can process complex sensory input ...and also compute really complex functions Reinforcement Learning?? =can choose complex actions Deep Reinforcement Learning?using neural networks to approximate functions Policies (select next action) Value functionsmeasure goodness of states or state-action pairsDynamics Modelspredict next states and rewards Deep LearningDR ReinforcementL Learning 1. What is the deep reinforcement learning？EnvironmentPerceptsdata CNN RNN…PoliceValue function Dynamic modelActionsApproximated by Neural NetworkANN, RNN,CNN GAN,… 1