斯坦福、伯克利、杜克大学、哥大等 深度学习课程+书籍

888888

深度学习是机器学习研究中的一个新的领域，其动机在于建立、模拟人脑进行分析学习的神经网络，它模仿人脑的机制来解释数据，例如图像，声音和文本。

【课程内容】

Audio Signal Processing for Music Applications

• Introduction
• Discrete Fourier transform
• Fourier theorems
• Short-time Fourier transform
• Sinusoidal model
• Harmonic model
• Sinusoidal plus residual model
• Sound transformations
• Sound and music description
• Concluding topics
  

Computer Vision 计算机视觉

• Overview
• Fundamentals of image formation
• Rigid body motion
• Orthogonal transformations
• Orthogonal transformations - Orthogonal Matrices
• Orthogonal matrices - Rotations and reflections
• Parametrizing Rotations in 3D
• Euclidean, Affine and Projective Transformations
• Dynamic Perspective
• Binocular Stereo
• Radiometry
• Image processing
• Orientation histograms
• Handwritten digit recognition - Introduction
• Support Vector Machines
• Transformation Invariance and Histograms
• Digit recognition using SVMs
• Random forests
• Detection of 3D objects
• Concluding Remarks
  

Image and video processing

• What is image and video processing
• Course logistics
• Images are everywhere
• Human visual system
• Image formation - Sampling  Quantization
• Simple image operations
• The why and how of compression
• Huffman coding
• JPEGs 8x8 blocks
• The Discrete Cosine Transform (DCT)
• Quantization
• JPEG_LS and MPEG
• Bonus Run-length compression
• Introduction to image enhancement
• Demo - Enhancement Histogram modification
• Histogram equalization
• Histogram matching
• Introduction to local neighborhood operations
• Mathematical properties of averaging
• Non-Local means
• IPOL Demo - Non-Local means
• Median filter
• Demo - Median filter
• Derivatives Laplacian  Unsharp masking
• Demo - Unsharp masking
• Gradients of scalar and vector images
• Concluding remarks
• What is image restoration
• Noise types
• Demo - Types of noise
• Noise and histograms
• Estimating noise
• Degradation Function
• Wiener filtering
• Demo - Wiener and Box filters
• Concluding remarks
• Introduction to Segmentation
• On Edges and Regions
• Hough Transform with Matlab Demo
• Line Segment Detector with Demo
• Otsus Segmentation with Demo
• Congratulations
• Interactive Image Segmentation
• Graph Cuts and Ms Office
• Mumford-Shah
• Active Contours - Introduction with ipol.im and Photoshop Demos
• Behind the Scenes of Adobes Roto Brush
• Introduction to PDEs in Image and Video Processing
• Planar Differential Geometry
• Surface Differential Geometry
• Curve Evolution
• Level Sets and Curve Evolution
• Calculus of Variations
• Anisotropic Diffusion
• Active Contours
• Bonus Cool Contrast Enhancement via PDEs
• Introduction to Image Inpainting
• Inpainting in Nature
• PDEs and Inpainting
• Inpainting via Calculus of Variations
• Smart Cut and Paste
• Demo - Photoshop Inpainting Healing Brush
• Video Inpainting and Conclusions
• Introduction to Sparse Modeling
• Sparse Modeling - Implementation
• Dictionary Learning
• Sparse Modeling Image Processing Examples
• A Note on Compressed Sensing
• GMM and Structured Sparsity
• Bonus Sparse Modeling and Classification - Activity Recognition
• Introduction to Medical Imaging
• Image Processing and HIV
• Brain Imaging Diffusion Imaging Deep Brain Stimulation
  

Natural Language Processing Collins

• Introduction to Natural Language Processing
• The Language Modeling Problem
• Parameter Estimation in Language Models
• Summary
• Tagging Problems and Hidden Markov Models
• Parsing and Context-Free Grammars
• Probabilistic Context-Free Grammars
• Weaknesses of PCFGs
• Lexicalized PCFGs
• Introduction to Machine Translation
• The IBM Translation Models
• Phrase-based Translation Models
• Decoding of Phrase-based Translation Models
• Log-linear Models
• Log-linear Models for Tagging
• Log-Linear Models for History-based Parsing
• Unsupervised Learning- Brown Clustering
• Global Linear Models
• GLMs for Tagging
• GLMs for Dependency Parsing
  

Neural Networks for Machine Learning

• hinton-ml(67课)
• neuralnets（78课）
  

Probabilistic Graphical Models

• Introduction and Overview
• Bayesian Network Fundamentals
• Template Models
• ML-class Octave Tutorial
• Structured CPDs
• Markov Network Fundamentals
• Representation Wrapup- Knowledge Engineering
• Inference-Variable Elimination
• Inference-Belief Propagation
• Inference-MAP Estimation
• Inference-Sampling Methods
• Inference-Temporal Models and Wrap-up
• Decision Theory
• ML-class Revision
• Learning-Overview
• Learning-Parameter Estimation in BNs
• Learning-Parameter Estimation in MNs
• Structure Learning
• Learning With Incomplete Data
• Learning-Wrapup
• Summary
  

《深度学习在互联网上的应用》

神经网络、深度学习方向书籍资料

• A Note on BPTT for LSTM LM.pdf
• cnn-lstm-ctc.pdf
• CNN与反向传播.pdf
• ctc.pdf
• Deep learning(1).pdf
• Deep Learning-Bengio .pdf
• deep learning.pdf
• deep-learning-nature2015.pdf
• deeplearning.pdf
• deeplearningbook-chinese-master.zip
• DeepLearningBook.pdf
• DeepLearning_MethodsandApplications-MR-Chinese.pdf
• deep_rl_tutorial.pdf
• Hinton.SOM.pdf
• Introduction to Deep Learning.pdf
• Neural Network and Deep Learning.pdf
• Supervised Sequence Labelling with Recurrent Neural Networks.pdf
• tr.pdf
• Unsupervised Learning of Edges_Yin Li_2016.pdf
• Week1d Introduction to CNNs (AlexNet).pdf
• 《神经网络与深度学习》邱锡鹏
• 《神经网络与深度学习综述DeepLearning15May2014.pdf
• 人工智能深度学习deeplearning_for_AI_course(2015_Spring)_927202100.pdf
• 刘昕 - 深度学习基础与实战_2017新版.pdf
• 可视化理解卷积网络Visualizing and Understanding Convolutional Networks.pdf
• 吴恩达深度学习基础教程.pdf
• 基于CNN的图片颜色处理.pdf
• 基于卷积神经网络的深度学习算法与应用研究.pdf
• 大数据，机器(深度）学习精品名师学习课程.pdf
• 深度学习.rar
• 深度学习word2vec学习笔记.pdf
• 深度学习基础及数学原理.pdf
• 深度学习基础教程.pdf
• 深度学习的基本理论与方法.pptx
• 电子书_深度学习方法及应用.pdf
• 神经网络和深度学习.pdf
• 神经网络与机器学习（原书第3版）.pdf
• 神经网络与深度学习讲义20151211.pdf
• 神经网络原理.pdf
  

本资源来源于 网络 付费网站  付费收集而来, 随时收集更新资源  本站专注搜集和分享各种付费网站资源,感谢您的信任


资源下载地址:

游客，如果您要查看本帖隐藏内容请回复>>>开通VIP无需回帖直接下载VIP通道

本站所有资源都来源于网络收集,网友提供或者交换而来!

如果侵犯了您的权益,请及时联系客服,我们即刻删除!