==人工智能定义序言==
人工智能,是指计算机系统具备从听说读写到搜索、推理、决策和回答问题等类人智能的能力技术科学的进步历程往往是理论通过实践开辟道路的过程。
感知、理解、决策== 人工/机器智能 ==
==人工智能历史==[[人工智能]]/机器智能(Artificial / Machine Intelligence),是指计算机系统具备从听说读写到搜索、推理、决策和回答问题等类人智能的能力,即感知、理解、决策的能力。
过去经历了2次高潮与2次低谷[[人工智能实现思路]]
网络和云计算所支持的计算能力=== 发展历史 ===
基于大数据的机器学习的算法进步[[人工神经网络的历史]]
阅读材料:=实验竞赛数据集 =
# The rebirth of neural networks-ISCA-2010 [http://pages.saclay.inria.fr/olivier.temam/homepage/ISCA2010web.pdf rebirth_NN[实验数据集]]
==国际研究深度学习 ==
[http://research.google.com/teams/brain/ Googel_Brain]([http://research.google.com/pubs/jeff.html Jeff Dean])深度学习(Deep Learning),机器学习中一种基于对数据进行表征学习的方法,试图使用包含复杂结构或由多重非线性变换构成的多个处理层对数据进行高层抽象的算法。
[https://research.facebook.com/ai Facebook_AI-Research[深度学习]](Yann LeCun)
[https://www.openai.com/blog/ OpenAI](Ilya Sutskever)== 增强学习 ==
==四个层面==增强学习(Reinforcement Learning),是机器学习中的一个领域,强调如何基于环境而行动,以取得最大化的预期利益。
===目标与功能分类===[[增强学习]]
语音识别 机器视觉 智能问答== 机器感知 ==
===核心技术分类===机器感知(Machine Perception),如语音,图像,视频,手势,姿态等
特定算法 机器学习算法 深度神经网络=== 语音识别 ===
===软件工具===TensorFlow / Caffe / Torch[[语音识别]],Automatic Speech Recognition,简称ASR
===底层硬件分类计算机视觉 ===
可编程逻辑阵列 FPGA / 通用图形处理器 GPGPU / 通用处理器 CPU 群集[[计算机视觉]],Computer Vision,简称CV
==机器感知机器认知 ==
===语音识别===机器认知(Machine Cognition),自然语言理解、推理、注意、知识、学习、决策、交互等。
语音识别(Automatic Speech Recognition),简称ASR'''技术手段:'''深度学习(Deep Learning)+ 增强学习(Reinforcement Learning)
# Google Speech Processing from Mobile to Farfield, CHiME 2016. [http://spandh.dcs.shef.ac.uk/chime_workshop/presentations/CHiME_2016_Bacchiani_keynote.pdf Google_Speech_Processing]=== 自然语言理解 ===
===计算机视觉===自然语言理解(Natural Language Understanding),使用的技术称为自然语言处理(Natural Language Processing,简称NLP)。
计算机视觉(Computer Vision),简称 CV=== 智能问答 ===
* Object Detection:<B>R-CNN (Region-based Convolutional Network method)</B>#Region based convolutional networks for accurate object detection and segmentation. TPAMI, 2015.#Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR 2014.整合语音识别ASR,计算机视觉CV和自然语言处理NLP的问答系统QA。
:<B>Fast R-CNN (Fast Region-based Convolutional Network method)</B>#Fast R-CNN, ICCV 2015.==语音合成==
:<B>Faster R-CNN (Faster Region-based Convolutional Network method)</B>#Faster R-CNN Towards real-time object detection with region proposal networks, NIPS, 2015.[[语音合成]]
===自然语言理解=计算机游戏 ==
自然语言理解(Natural Language Processing),简称NLP[[计算机游戏]]
==机器学习机器翻译==
Machine Learning[[机器翻译]]
[http://scikit-learn.org scikit-learn]==推荐系统==
# Jordan, M. I., and T. M. Mitchell. "Machine learning: Trends, perspectives, and prospects." Science 349, no. 6245 (2015): 255-260. [http://science.sciencemag.org/content/349/6245/255 Machine_learning_science_2015[推荐系统]]
==深度神经网络==
[[卷积神经网络]]
Deep Neural Networks,简称DNN Stanford Deep Learning tutorials [http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial DL_tutorials] 入门导读 # LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521(7553), pp:436-444, 2015. [http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html Deep_Learning_Nature]# Jeff Dean, Large-Scale Deep Learning for Intelligent Computer Systems, WSDM 2016. [http://research.google.com/pubs/jeff.html WSDM_keynote]# Jeffrey Dean et al. "Large scale distributed deep networks." Advances in Neural Information Processing Systems. 2012.# TensorFlow: A System for Large-Scale Machine Learning, OSDI 2016. [https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf TensorFlow_OSDI2016_paper] [http://research.google.com/pubs/pub45381.html TensorFlow_paper] ==深度学习工具== ===谷歌=== [https://github.com/tensorflow/tensorflow TensorFlow] [http://download.tensorflow.org/paper/whitepaper2015.pdf Google_TensorFlow_whitepaper] ===微软=== [http://cntk.ai CNTK_Microsfot] [https://www.microsoft.com/en-us/research/product/cognitive-toolkit/tutorials/ CNTK] ===百度=== [https://github.com/dmlc/mxnet dmlc_mxnet] ==智能问答相关资料==
相关课程:
[[实验室探究课-智能问答与智能系统]]