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

Training a Neural Network

After network architecture and activation functions, the last design step before you can start training a neural network is the choice of loss function.

We will start with an overview of possible loss functions for regression, binary classification, and multiclass classification problems. Then, we will introduce some optimizers and additional training parameters for the training algorithms.

Loss Functions

In order to train a feedforward neural network, an appropriate error function, often called a loss function, and a matching last layer have to be selected. Let's start with an overview of commonly used loss functions for regression problems.

Loss Functions for Regression Problems

In the case of a regression problem, where the goal is to predict one single numerical value, the output layer should have one unit only and use the linear activation function. Possible loss functions to train this kind of network must refer to numerical error...