舉報 
會員
Hands-On Deep Learning with Apache Spark
Deeplearningisasubsetofmachinelearningwheredatasetswithseverallayersofcomplexitycanbeprocessed.Hands-OnDeepLearningwithApacheSparkaddressesthesheercomplexityoftechnicalandanalyticalpartsandthespeedatwhichdeeplearningsolutionscanbeimplementedonApacheSpark.ThebookstartswiththefundamentalsofApacheSparkanddeeplearning.YouwillsetupSparkfordeeplearning,learnprinciplesofdistributedmodeling,andunderstanddifferenttypesofneuralnets.Youwillthenimplementdeeplearningmodels,suchasconvolutionalneuralnetworks(CNNs),recurrentneuralnetworks(RNNs),andlongshort-termmemory(LSTM)onSpark.Asyouprogressthroughthebook,youwillgainhands-onexperienceofwhatittakestounderstandthecomplexdatasetsyouaredealingwith.Duringthecourseofthisbook,youwillusepopulardeeplearningframeworks,suchasTensorFlow,Deeplearning4j,andKerastotrainyourdistributedmodels.Bytheendofthisbook,you'llhavegainedexperiencewiththeimplementationofyourmodelsonavarietyofusecases.
目錄(158章)
倒序
- coverpage
- Title Page
- Copyright and Credits
- Hands-On Deep Learning with Apache Spark
- 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
- Download the color images
- Conventions used
- Get in touch
- Reviews
- The Apache Spark Ecosystem
- Apache Spark fundamentals
- Getting Spark
- RDD programming
- Spark SQL Datasets and DataFrames
- Spark Streaming
- Cluster mode using different managers
- Standalone mode
- Mesos cluster mode
- YARN cluster mode
- Submitting Spark applications on YARN
- Kubernetes cluster mode
- Summary
- Deep Learning Basics
- Introducing DL
- DNNs overview
- CNNs
- RNNs
- Practical applications of DL
- Summary
- Extract Transform Load
- Training data ingestion through Spark
- The DeepLearning4j framework
- Data ingestion through DataVec and transformation through Spark
- Training data ingestion from a database with Spark
- Data ingestion from a relational database
- Data ingestion from a NoSQL database
- Data ingestion from S3
- Raw data transformation with Spark
- Summary
- Streaming
- Streaming data with Apache Spark
- Streaming data with Kafka and Spark
- Apache Kakfa
- Spark Streaming and Kafka
- Streaming data with DL4J and Spark
- Summary
- Convolutional Neural Networks
- Convolutional layers
- Pooling layers
- Fully connected layers
- Weights
- GoogleNet Inception V3 model
- Hands-on CNN with Spark
- Summary
- Recurrent Neural Networks
- LSTM
- Backpropagation Through Time (BPTT)
- RNN issues
- Use cases
- Hands-on RNNs with Spark
- RNNs with DL4J
- RNNs with DL4J and Spark
- Loading multiple CSVs for RNN data pipelines
- Summary
- Training Neural Networks with Spark
- Distributed network training with Spark and DeepLearning4j
- CNN distributed training with Spark and DL4J
- RNN distributed training with Spark and DL4J
- Performance considerations
- Hyperparameter optimization
- The Arbiter UI
- Summary
- Monitoring and Debugging Neural Network Training
- Monitoring and debugging neural networks during their training phases
- 8.1.1 The DL4J training UI
- 8.1.2 The DL4J training UI and Spark
- 8.1.3 Using visualization to tune a network
- Summary
- Interpreting Neural Network Output
- Evaluation techniques with DL4J
- Evaluation for classification
- Evaluation for classification – Spark example
- Other types of evaluation
- Summary
- Deploying on a Distributed System
- Setup of a distributed environment with DeepLearning4j
- Memory management
- CPU and GPU setup
- Building a job to be submitted to Spark for training
- Spark distributed training architecture details
- Model parallelism and data parallelism
- Parameter averaging
- Asynchronous stochastic gradient sharing
- Importing Python models into the JVM with DL4J
- Alternatives to DL4J for the Scala programming language
- BigDL
- DeepLearning.scala
- Summary
- NLP Basics
- NLP
- Tokenizers
- Sentence segmentation
- POS tagging
- Named entity extraction (NER)
- Chunking
- Parsing
- Hands-on NLP with Spark
- Hands-on NLP with Spark and Stanford core NLP
- Hands-on NLP with Spark NLP
- Summary
- Textual Analysis and Deep Learning
- Hands-on NLP with DL4J
- Hands-on NLP with TensorFlow
- Hand-on NLP with Keras and a TensorFlow backend
- Hands-on NLP with Keras model import into DL4J
- Summary
- Convolution
- Convolution
- Object recognition strategies
- Convolution applied to image recognition
- Keras implementation
- DL4J implementation
- Summary
- Image Classification
- Implementing an end-to-end image classification web application
- Picking up a proper Keras model
- Importing and testing the model in DL4J
- Re-training the model in Apache Spark
- Implementing the web application
- Implementing a web service
- Summary
- What's Next for Deep Learning?
- What to expect next for deep learning and AI
- Topics to watch for
- Is Spark ready for RL?
- DeepLearning4J future support for GANs
- Summary
- Appendix A: Functional Programming in Scala
- Functional programming (FP)
- Purity
- Recursion
- Appendix B: Image Data Preparation for Spark
- Image preprocessing
- Strategies
- Training
- Other Books You May Enjoy
- Leave a review - let other readers know what you think 更新時間：2021-07-02 13:34:49
推薦閱讀
- 繪制進程圖：可視化D++語言（第1冊）
- Mastering Matplotlib 2.x
- Practical Ansible 2
- 傳感器技術實驗教程
- 人工智能工程化：應用落地與中臺構建
- Python Data Science Essentials
- 計算機網絡技術基礎
- Linux：Powerful Server Administration
- Visual FoxPro數據庫基礎及應用
- Hands-On Data Warehousing with Azure Data Factory
- AVR單片機工程師是怎樣煉成的
- 未來學徒：讀懂人工智能飛馳時代
- 大數據導論
- Machine Learning with Spark（Second Edition）
- PowerPoint 2003中文演示文稿5日通
- 多傳感器數據智能融合理論與應用
- Cloud Native Development Patterns and Best Practices
- Oracle Fusion Applications Administration Essentials
- Selenium測試實踐
- Hands-On Internet of Things with Blynk
- UGNX 5三維造型
- 計算機網絡
- 人工智能初探1
- IBM SPSS Modeler Essentials
- Arduino創意機器人入門
- 移動機器人導航定位技術
- Presto實戰
- PostgreSQL 11 Administration Cookbook
- Voicebot and Chatbot Design
- Flex3.0 RIA開發詳解
