“大数据智能”版本间的差异
(→机器认知) |
|||
第95行: | 第95行: | ||
[https://github.com/Theano/Theano/ Theano_code] | [https://github.com/Theano/Theano/ Theano_code] | ||
+ | |||
+ | =增强学习= | ||
+ | 增强学习(Reinforcement Learning) | ||
+ | |||
+ | ==增强学习入门材料== | ||
+ | An Introduction to Reinforcement Learning | ||
+ | [http://webdocs.cs.ualberta.ca/~sutton/book/the-book.html Intro_RL] | ||
+ | |||
+ | Algorithms for Reinforcement Learning | ||
+ | [http://www.ualberta.ca/~szepesva/papers/RLAlgsInMDPs.pdf RLAlgsInMDPs] | ||
+ | |||
+ | ==工具== | ||
+ | ===谷歌=== | ||
+ | deepmind/lab | ||
+ | [https://github.com/deepmind/lab deepmind_lab] | ||
+ | |||
+ | ===OpenAI=== | ||
+ | openai/universe | ||
+ | [https://github.com/openai/universe openai_universe] | ||
+ | |||
=机器感知= | =机器感知= | ||
第142行: | 第162行: | ||
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。 | 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。 | ||
− | |||
<B>技术手段:</B> | <B>技术手段:</B> | ||
深度学习(Deep Learning) + 增强学习(Reinforcement/Unsupervised Learning) | 深度学习(Deep Learning) + 增强学习(Reinforcement/Unsupervised Learning) | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
=前沿应用进展= | =前沿应用进展= |
2017年1月9日 (一) 03:36的版本
人工智能简介
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。即, 感知、理解、决策的能力。
人工智能历史
过去经历了2次高潮与2次低谷
网络和云计算所支持的计算能力
基于大数据的机器学习的算法进步
阅读材料:
- The rebirth of neural networks-ISCA-2010 rebirth_NN
四个层面
目标与功能分类
语音识别、机器视觉、自然语言理解。
智能问答是综合以上功能的高级系统。
核心技术分类
特定算法 机器学习算法 深度神经网络
软件工具
TensorFlow / Caffe / Torch
底层硬件分类
可编程逻辑阵列 FPGA / 通用图形处理器 GPGPU / 通用处理器 CPU 群集
国际研究
Facebook_AI-Research (Yann LeCun)
MSR Deep Learning Technology Center (DLTC) (Li Deng)
OpenAI (Ilya Sutskever)
机器学习
Machine Learning
- Jordan, M. I., and T. M. Mitchell. "Machine learning: Trends, perspectives, and prospects." Science 349, no. 6245 (2015): 255-260. Machine_learning_science_2015
深度学习
Deep Neural Networks,简称DNN
深度学习工具
谷歌
微软
DMLC
Université de Montréal
增强学习
增强学习(Reinforcement Learning)
增强学习入门材料
An Introduction to Reinforcement Learning Intro_RL
Algorithms for Reinforcement Learning RLAlgsInMDPs
工具
谷歌
deepmind/lab deepmind_lab
OpenAI
openai/universe openai_universe
机器感知
机器感知(Machine Perception),如语音,图像,视频,手势,姿态等
基于深度学习的机器感知
语音识别
语音识别(Automatic Speech Recognition),简称ASR
- Google Speech
- Google Speech Processing from Mobile to Farfield, CHiME 2016. Google_Speech_Processing
- Long short term memory neural network (LSTM)
- Long short term memory neural computation, Neural computation 9 (8), 1735-1780, 1997. LSTM
- Connectionist temporal classification (CTC)
- Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks, ICML 2006.
- Gated Recursive Unit (GRU)
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches, SSST-8, 2014.
计算机视觉
计算机视觉(Computer Vision),简称 CV
- Object Detection
- R-CNN (Region-based Convolutional Network method)
- Region based convolutional networks for accurate object detection and segmentation, TPAMI, 2015.
- Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR 2014.
- Fast R-CNN (Fast Region-based Convolutional Network method)
- Fast R-CNN, ICCV 2015.
- Faster R-CNN (Faster Region-based Convolutional Network method)
- Faster R-CNN Towards real-time object detection with region proposal networks, NIPS, 2015.
- • Fast_R-CNN(Python): https://github.com/rbgirshick/fast-rcnn
- • Faster_R-CNN(matlab): https://github.com/ShaoqingRen/faster_rcnn
- • Faster_R-CNN(Python): https://github.com/rbgirshick/py-faster-rcnn
机器认知
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。
技术手段:
深度学习(Deep Learning) + 增强学习(Reinforcement/Unsupervised Learning)
前沿应用进展
自然语言理解
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)
智能问答
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。
Reasoning in vector space: An exploratory study of question answering, ICLR 2016.