Book Image

Codeless Deep Learning with KNIME

By : Kathrin Melcher, KNIME AG, Rosaria Silipo
Book Image

Codeless Deep Learning with KNIME

By: Kathrin Melcher, KNIME AG, Rosaria Silipo

Overview of this book

KNIME Analytics Platform is an open source software used to create and design data science workflows. This book is a comprehensive guide to the KNIME GUI and KNIME deep learning integration, helping you build neural network models without writing any code. It’ll guide you in building simple and complex neural networks through practical and creative solutions for solving real-world data problems. Starting with an introduction to KNIME Analytics Platform, you’ll get an overview of simple feed-forward networks for solving simple classification problems on relatively small datasets. You’ll then move on to build, train, test, and deploy more complex networks, such as autoencoders, recurrent neural networks (RNNs), long short-term memory (LSTM), and convolutional neural networks (CNNs). In each chapter, depending on the network and use case, you’ll learn how to prepare data, encode incoming data, and apply best practices. By the end of this book, you’ll have learned how to design a variety of different neural architectures and will be able to train, test, and deploy the final network.
Table of Contents (16 chapters)
1
Section 1: Feedforward Neural Networks and KNIME Deep Learning Extension
6
Section 2: Deep Learning Networks
12
Section 3: Deployment and Productionizing

Questions and Exercises

Check your level of understanding of the concepts explored in this chapter by answering the following questions:

  1. Why are LSTM units suitable for time series analysis?

    a). Because they are faster than classic feedforward networks

    b). Because they can remember past input tensors

    c). Because they use gates

    d). Because they have hidden states

  2. What is the data extraction option to use for partitioning in time series analysis?

    a). Draw randomly

    b). Take from top

    c). Stratified Sampling

    d). Linear Sampling

  3. What is a tensor?

    a). A tensor is a two-dimensional vector.

    b). A tensor is a k-dimensional vector.

    c). A tensor is just a number.

    d). A tensor is a sequence of numbers.

  4. What is the difference between in-sample and out-sample testing?

    a). In-sample testing uses the real past values from the test set to make the predictions. Out-sample testing uses past prediction values to make new predictions.

    b). In-sample testing is more realistic than out-sample testing...