舉報 
會員
Go Machine Learning Projects
Goistheperfectlanguageformachinelearning;ithelpstoclearlydescribecomplexalgorithms,andalsohelpsdeveloperstounderstandhowtorunefficientoptimizedcode.ThisbookwillteachyouhowtoimplementmachinelearninginGotomakeprogramsthatareeasytodeployandcodethatisnotonlyeasytounderstandanddebug,butalsotohaveitsperformancemeasured.ThebookbeginsbyguidingyouthroughsettingupyourmachinelearningenvironmentwithGolibrariesandcapabilities.Youwillthenplungeintoregressionanalysisofareal-lifehousepricingdatasetandbuildaclassificationmodelinGotoclassifyemailsasspamorham.UsingGonum,Gorgonia,andSTL,youwillexploretimeseriesanalysisalongwithdecompositionandcleanupyourpersonalTwittertimelinebyclusteringtweets.Inadditiontothis,youwilllearnhowtorecognizehandwritingusingneuralnetworksandconvolutionalneuralnetworks.Lastly,you'lllearnhowtochoosethemostappropriatemachinelearningalgorithmstouseforyourprojectswiththehelpofafacialdetectionproject.Bytheendofthisbook,youwillhavedevelopedasolidmachinelearningmindset,astrongholdonthepowerfulGotoolkit,andasoundunderstandingofthepracticalimplementationsofmachinelearningalgorithmsinreal-worldprojects.
目錄(210章)
倒序
- coverpage
- Title Page
- About Packt
- Why subscribe?
- Packt.com
- Contributors
- About the author
- About the reviewer
- Packt is searching for authors like you
- Preface
- Who this book is for
- What this book covers
- To get the most out of this book
- Download the example code files
- Conventions used
- Get in touch
- Reviews
- How to Solve All Machine Learning Problems
- What is a problem?
- What is an algorithm?
- What is machine learning?
- Do you need machine learning?
- The general problem solving process
- What is a model?
- What is a good model?
- On writing and chapter organization
- Why Go?
- Quick start
- Functions
- Variables
- Values
- Types
- Methods
- Interfaces
- Packages and imports
- Let's Go!
- Linear Regression - House Price Prediction
- The project
- Exploratory data analysis
- Ingestion and indexing
- Janitorial work
- Encoding categorical data
- Handling bad numbers
- Final requirement
- Writing the code
- Further exploratory work
- The conditional expectation functions
- Skews
- Multicollinearity
- Standardization
- Linear regression
- The regression
- Cross-validation
- Running the regression
- Discussion and further work
- Summary
- Classification - Spam Email Detection
- The project
- Exploratory data analysis
- Tokenization
- Normalizing and lemmatizing
- Stopwords
- Ingesting the data
- Handling errors
- The classifier
- Naive Bayes
- TF-IDF
- Conditional probability
- Features
- Bayes' theorem
- Implementating the classifier
- Class
- Alternative class design
- Classifier part II
- Putting it all together
- Summary
- Decomposing CO2 Trends Using Time Series Analysis
- Exploratory data analysis
- Downloading from non-HTTP sources
- Handling non-standard data
- Dealing with decimal dates
- Plotting
- Styling
- Decomposition
- STL
- LOESS
- The algorithm
- Using STL
- How to lie with statistics
- More plotting
- A primer on Gonum plots
- The residuals plotter
- Combining plots
- Forecasting
- Holt-Winters
- Summary
- References
- Clean Up Your Personal Twitter Timeline by Clustering Tweets
- The project
- K-means
- DBSCAN
- Data acquisition
- Exploratory data analysis
- Data massage
- The processor
- Preprocessing a single word
- Normalizing a string
- Preprocessing stopwords
- Preprocessing Twitter entities
- Processing a single tweet
- Clustering
- Clustering with K-means
- Clustering with DBSCAN
- Clustering with DMMClust
- Real data
- The program
- Tweaking the program
- Tweaking distances
- Tweaking the preprocessing step
- Summary
- Neural Networks - MNIST Handwriting Recognition
- A neural network
- Emulating a neural network
- Linear algebra 101
- Exploring activation functions
- Learning
- The project
- Gorgonia
- Getting the data
- Acceptable format
- From images to a matrix
- What is a tensor?
- From labels to one-hot vectors
- Visualization
- Preprocessing
- Building a neural network
- Feed forward
- Handling errors with maybe
- Explaining the feed forward function
- Costs
- Backpropagation
- Training the neural network
- Cross-validation
- Summary
- Convolutional Neural Networks - MNIST Handwriting Recognition
- Everything you know about neurons is wrong
- Neural networks – a redux
- Gorgonia
- Why?
- Programming
- What is a tensor? – part 2
- All expressions are graphs
- Describing a neural network
- One-hot vector
- The project
- Getting the data
- Other things from the previous chapter
- CNNs
- What are convolutions?
- How Instagram filters work
- Back to neural networks
- Max-pooling
- Dropout
- Describing a CNN
- Backpropagation
- Running the neural network
- Testing
- Accuracy
- Summary
- Basic Facial Detection
- What is a face?
- Viola-Jones
- PICO
- A note on learning
- GoCV
- API
- Pigo
- Face detection program
- Grabbing an image from the webcam
- Displaying the image
- Doodling on images
- Face detection 1
- Face detection 2
- Putting it all together
- Evaluating algorithms
- Summary
- Hot Dog or Not Hot Dog - Using External Services
- MachineBox
- What is MachineBox?
- Signing in and up
- Docker installation and setting up
- Using MachineBox in Go
- The project
- Training
- Reading from the Webcam
- Prettifying the results
- The results
- What does this all mean?
- Why MachineBox?
- Summary
- What's Next?
- What should the reader focus on?
- The practitioner
- The researcher
- The researcher the practitioner and their stakeholder
- What did this book not cover?
- Where can I learn more?
- Thank you
- Other Books You May Enjoy
- Leave a review - let other readers know what you think 更新時間：2021-06-10 18:47:12
推薦閱讀
- 空間機器人遙操作系統及控制
- 2018西門子工業專家會議論文集(上)
- 條碼技術及應用
- 西門子S7-200 SMART PLC實例指導學與用
- Ceph：Designing and Implementing Scalable Storage Systems
- 新編計算機圖形學
- 液壓機智能故障診斷方法集成技術
- 工業自動化技術實訓指導
- 人工智能技術入門
- Visual C++項目開發案例精粹
- Mastering Text Mining with R
- 寒江獨釣：Windows內核安全編程
- Dreamweaver+Photoshop+Flash+Fireworks網站建設與網頁設計完全實用
- 人工智能：智能人機交互
- 中文版Photoshop情境實訓教程
- 百度智能小程序：AI賦能新機遇
- SQL語言與數據庫操作技術大全
- 洞察大數據價值：SAS編程與數據挖掘
- 數字孿生技術與工程實踐：模型+數據驅動的智能系統
- R Programming By Example
- 黑客攻防實戰編程
- Big Data Analysis with Python
- 主數據驅動的數據治理：原理、技術與實踐
- 初入職場之嵌入式Linux開發快速上手
- Photoshop CS3中文版圖像處理與創意設計
- Visual C++.NET串口通信及測控應用典型實例
- Machine Learning with R
- 第十三屆中國智能交通年會優秀論文集
- 叩響智能制造的大門（全5冊）
- Troubleshooting vSphere Storage
