logo资料库

Deep Belief Nets in C++ and CUDA C Volume 2.pdf

发布时间：2022-05-29 发布人：admin 分类：说明书 资料大小：5.51M 资料格式：pdf 举报 版权申诉
第1页 / 共265页
第2页 / 共265页
第3页 / 共265页
第4页 / 共265页
第5页 / 共265页
第6页 / 共265页
第7页 / 共265页
第8页 / 共265页
资料共265页，剩余部分请下载后查看
    Table of Contents
    About the Author
    About the Technical Reviewer
    Introduction
    Chapter 1: Embedded Class Labels
    Code for Learning Embedded Labels
    Cross Entropy Reconstruction Error
    Fast vs. Slow Reconstruction Error Computation
    Classifying Cases
    Class-Conditional Generative Sampling
    Chapter 2: Signal Preprocessing
    Simple, Minimal Transformation
    Logs and Differences
    Windows and Shifting
    Pseudocode for Simple Series Processing
    Tail Trimming
    Example of Simple Series Creation
    Displaying Differenced Generative Samples
    Path of a Function
    Pseudocode for Series Path Computation
    Example of Path Series Creation
    Fourier Coefficients in a Moving Window
    Pseudocode for Fourier Series Processing
    Example of Fourier Series Generation
    Length=10 with No Centering
    Length=10 with Centering
    Length=11 with No Centering
    Length=11 with Centering
    Morlet Wavelets
    Period, Width, and Lag
    Code for Morlet Wavelets
    Example of Morlet Wavelet Series Generation
    Path in an XY Plane
    Normalization for Invariance
    Pseudocode for XY Plane Series Processing
    Example of XY Plane Series Processing
    Chapter 3: Image Preprocessing
    The Fourier Transform in Two Dimensions
    Data Windows in Two Dimensions
    Code for the Fourier Transform of an Image
    Displaying Generative Samples of Fourier Transforms
    Chapter 4: Autoencoding
    Basic Mathematics of Feedforward Networks
    Greedy Training with Autoencoders
    Review of Complex Numbers
    Fast Dot Product Computation in the Complex Domain
    Singular Value Decomposition in the Complex Domain
    Activation in the Complex Domain
    Derivatives of the Activation Function
    The Logistic Activation Function and Its Derivative
    Computing the Gradient
    Pure Real and SoftMax Output Errors
    Gradient of the Hidden-Layer Weights
    Code for Gradient Computation
    Evaluating the Entire Network and Derivatives
    Computing the Gradient
    Multithreading Gradient Computation
    CUDA Gradient Computation
    The Overall Algorithm
    Device Initialization
    Copying Weights from Host to Device
    Activation and Its Derivatives
    Output Activation
    SoftMax Modification of Outputs
    Output Delta
    Delta for SoftMax Outputs
    Output Gradient
    Gradient of the First Hidden Layer
    Gradient of a Subsequent Hidden Layer
    Mean Squared Error
    The Log Likelihood Criterion for Classification
    An Analysis
    Chapter 5: DEEP Operating Manual
    Menu Options
    File Menu Options
    Test Menu Options
    Display Menu Options
    Read a Database
    Read a Series (Simple)
    Read a Series (Trend Path)
    Read a Series (Fourier)
    Read a Series (Morlet)
    Read XY Points
    Read MNIST Image
    Read MNIST Image (Fourier)
    Read MNIST Labels
    Write Activation File
    Clear All Data
    Model Architecture
    Database Inputs and Targets
    RBM Training Params
    Supervised Training Params
    Autoencoding Training Params
    Train
    Test
    Cross Validate
    Analyze
    Receptive Field
    Generative Sample
    Samples from an Embedded Model
    Samples from a Path Series
    The DEEP.LOG File
    Predictive Performance Measures
    Index
    分享到：
    赞 收藏

    相关推荐

    资料库

    开发技术

    共收录19306份资料，累计14个分类，关注成员有19位，主要包括：Actionscript,Javascript,PHP,VB,Perl,Delphi,Python,C#,C,Java,C++,Web开发,硬件开发,其它

    热门标签

    Actionscript Javascript PHP VB Perl Delphi Python C# C Java C++ Web开发 硬件开发 其它

    最新资料