book

Codeless Deep Learning with KNIME

Name: Codeless Deep Learning with KNIME
ISBN: 9781800566613

by Kathrin Melcher, Rosaria Silipo

November 2020

Intermediate to advanced

384 pages

English

Packt Publishing

Read now

Unlock full access

Codeless Deep Learning with KNIME
Why subscribe?ContributorsAbout the authorsAbout the reviewersPackt is searching for authors like you
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example workflowsDownload the color imagesConventions usedGet in touchReviews
Section 1: Feedforward Neural Networks and KNIME Deep Learning Extension
Chapter 1: Introduction to Deep Learning with KNIME Analytics Platform
The Importance of Deep LearningExploring KNIME SoftwareKNIME Analytics PlatformKNIME Server for the EnterpriseExploring KNIME Analytics Platform Useful Links and MaterialsBuild and Execute Your First WorkflowInstalling KNIME Deep Learning – Keras IntegrationInstalling the Keras and TensorFlow NodesSetting up the Python EnvironmentGoal and Structure of this BookSummary
Chapter 2: Data Access and Preprocessing with KNIME Analytics Platform
Accessing DataReading Data from FilesData Types and ConversionsTransforming DataParameterizing the WorkflowSummaryQuestions and Exercises
Chapter 3: Getting Started with Neural Networks
Neural Networks and Deep Learning – Basic ConceptsArtificial Neuron and Artificial Neural Networks Signal Propagation within a Feedforward Neural NetworkUnderstanding the Need for Hidden LayersTraining a Multilayer PerceptronDesigning your NetworkCommonly Used Activation FunctionsRegularization Techniques to Avoid OverfittingOther Commonly used LayersTraining a Neural NetworkLoss FunctionsParameters and Optimization of the Training AlgorithmSummaryQuestions and Exercises
Chapter 4: Building and Training a Feedforward Neural Network
Preparing the DataDatasets and Classification ExamplesEncoding of Nominal FeaturesNormalizationOther Helpful Preprocessing NodesData Preparation on the Iris DatasetData Preparation on the Adult DatasetBuilding a Feedforward Neural ArchitectureThe Keras Input Layer NodeThe Keras Dense Layer NodeBuilding a Neural Network for Iris Flower ClassificationBuilding a Neural Network for Income PredictionTraining the NetworkSelecting the Loss FunctionDefining the Input and Output DataSetting the Training ParametersTracking the Training ProgressTraining Settings for Iris Flower ClassificationTraining Settings for Income PredictionTesting and Applying the NetworkExecuting the NetworkExtracting the Predictions and Evaluating the Network PerformanceTesting the Network Trained to Classify Iris FlowersTesting the Network Trained for Income PredictionSummaryQuestions and Exercises
Section 2: Deep Learning Networks
Chapter 5: Autoencoder for Fraud Detection
Introducing AutoencodersArchitecture of the AutoencoderReducing the Input Dimensionality with an AutoencoderDetecting Anomalies Using an AutoencoderWhy is Detecting Fraud so Hard?Building and Training the AutoencoderData Access and Data PreparationBuilding the AutoencoderTraining and Testing the AutoencoderDetecting Fraudulent TransactionsOptimizing the Autoencoder StrategyOptimizing Threshold Threshold is defined on a separate subset of data, called the optimization set. There are two options here:Deploying the Fraud DetectorReading Network, New Transactions, and Normalization ParametersApplying the Fraud DetectorTaking ActionsSummaryQuestions and Exercises
Chapter 6: Recurrent Neural Networks for Demand Prediction
Introducing RNNsRecurrent Neural NetworksRecurrent Neural UnitsLong Short-Term MemoryThe Demand Prediction ProblemDemand PredictionPredicting Energy DemandData Preparation – Creating the PastData Loading and StandardizationData Cleaning and PartitioningCreating the Input TensorsBuilding, Training, and Deploying an LSTM-Based RNNBuilding the LSTM-Based RNNTraining the LSTM-Based RNNTesting the LSTM-Based RNNBuilding a Deployment LoopDeploying the LSTM-Based RNNSummaryQuestions and Exercises

Chapter 7: Implementing NLP Applications
Exploring Text Encoding Techniques for Neural NetworksIndex EncodingOne-Hot Vector EncodingEmbeddings for Word EncodingFinding the Tone of Your Customers' Voice – Sentiment AnalysisPreprocessing Movie ReviewsDefining and Training the Network ArchitectureExecuting and Evaluating the Network on the Test SetGenerating Free Text with RNNsThe DatasetPredicting Words or Characters?Preprocessing and EncodingDefining and Training the Network ArchitectureBuilding a Deployment WorkflowThe New Fairy TaleGenerating Product Names with RNNsThe Problem of Product Name GenerationPreprocessing and Encoding Mountain NamesDefining and Training the Network ArchitectureBuilding a Deployment WorkflowSummaryQuestions and Exercises
Chapter 8: Neural Machine Translation
Idea of Neural Machine TranslationEncoder-Decoder ArchitectureApplying the EncoderApplying the Decoder during TrainingApplying the Decoder during DeploymentPreparing the Data for the Two LanguagesBuilding and Training the Encoder-Decoder ArchitectureDefining the Network StructureTraining the NetworkExtracting the Trained Encoder and DecoderApplying the Trained Network for Neural Machine TranslationSummaryQuestions and Exercises
Chapter 9: Convolutional Neural Networks for Image Classification
Introduction to CNNsHow are Images Stored?Why do we need CNNs?How does a Convolution Layer work?Introducing PaddingIntroducing Stride and Dilation RateIntroducing PoolingClassifying Images with CNNsReading and Preprocessing ImagesDesigning the NetworkTraining and Applying the NetworkPrediction Extraction and Model EvaluationIntroduction to transfer learningWhy use Transfer Learning?Formal Definition of Transfer LearningApplying Transfer LearningApplying Transfer Learning for Cancer Type PredictionDownloading the DatasetReading and Preprocessing the ImagesTraining the NetworkSummaryQuestions and Exercises
Section 3: Deployment and Productionizing
Chapter 10: Deploying a Deep Learning Network
Conversion of the Network Structure Saving a Trained NetworkReading a Trained NetworkUsing TensorFlow 2Building a Simple Deployment WorkflowBuilding a Deployment Workflow Manually, without Integrated DeploymentBuilding a Deployment Workflow Automatically with Integrated DeploymentImproving Scalability – GPU ExecutionSummaryQuestions and Exercises
Chapter 11: Best Practices and Other Deployment Options
Building a Web ApplicationIntroduction to KNIME WebPortal Creating a Workflow to Run on KNIME WebPortalCreating Composite ViewsShared ComponentsBuilding a WebPortal Application for Cancer Cell ClassificationBuilding a Web Service with the REST InterfaceBuilding a REST Service WorkflowKNIME Tips and TricksShuffling Data during TrainingUsing Batch NormalizationKeeping Your Workflow Clean and StructuredUsing the GroupBy Node and Pivoting Node to Avoid LoopsSpecifying the Execution OrderSummaryQuestions and Exercises
Other Books You May Enjoy
Leave a review - let other readers know what you think

Content preview from Codeless Deep Learning with KNIME

Chapter 9: Convolutional Neural Networks for Image Classification

In the previous chapters, we talked about Recurrent Neural Networks (RNNs) and how they can be applied to different types of sequential data and use cases. In this chapter, we want to talk about another family of neural networks, called Convolutional Neural Networks (CNNs). CNNs are especially powerful when used on data with grid-like topology and spatial dependencies, such as images or videos.

We will start with a general introduction to CNNs, explaining the basic idea behind a convolution layer and introducing some related terminology such as padding, pooling, filters, and stride.

Afterward, we will build and train a CNN for image classification from scratch. We will cover all ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781800566613

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Codeless Deep Learning with KNIME

by Kathrin Melcher, Rosaria Silipo

Chapter 9: Convolutional Neural Networks for Image Classification

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.