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

Building, Training, and Deploying an LSTM-Based RNN

Let's proceed with the next step: building a simple LSTM-based RNN for demand prediction. First, we will train the network, then we will test it, and finally, we will deploy it. In this case study, we used no validation set for the network and we performed no optimization on the static hyperparameters of the network, such as, for example, the size of the LSTM layer.

A relatively simple network is already achieving good error measures on the test set for our demand prediction task, and therefore, we decided to focus this section on how to test a model for time series prediction rather than on how to optimize the static parameters of a neural network. We looked at the optimization loop in Chapter 5, Autoencoder for Fraud Detection. In general, this optimization loop can also be applied to optimize network hyperparameters. Let's begin by building an LSTM-based RNN.

Building the LSTM-Based RNN

For this case study, we...