“大数据智能”版本间的差异

来自iCenter Wiki
跳转至: 导航搜索
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)
 
=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]
 
  
 
=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:

  1. 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

Googel_Brain (Jeff Dean)

Facebook_AI-Research (Yann LeCun)

MSR Deep Learning Technology Center (DLTC) (Li Deng)

OpenAI (Ilya Sutskever)

机器学习

Machine Learning

scikit-learn

  1. 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

卷积神经网络

深度学习-入门导读

深度学习工具

谷歌

TensorFlow

Google_TensorFlow_whitepaper

Facebook

fbcunn Torch

微软

CNTK_Microsfot

CNTK

DMLC

dmlc

MXNet dmlc_mxnet

Université de Montréal

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 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
  1. Google Speech Processing from Mobile to Farfield, CHiME 2016. Google_Speech_Processing
  • Long short term memory neural network (LSTM)
  1. Long short term memory neural computation, Neural computation 9 (8), 1735-1780, 1997. LSTM
  • Connectionist temporal classification (CTC)
  1. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks, ICML 2006.
  • Gated Recursive Unit (GRU)
  1. 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)
  1. Region based convolutional networks for accurate object detection and segmentation, TPAMI, 2015.
  2. Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR 2014.
Fast R-CNN (Fast Region-based Convolutional Network method)
  1. Fast R-CNN, ICCV 2015.
Faster R-CNN (Faster Region-based Convolutional Network method)
  1. 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.

其它课程

实验室探究课-智能问答与智能系统