The workflow downloads, uncompresses and preprocesses the orignal MNIST dataset from: http://yann.lecun.com/exdb/mnist/ The two "Normalize Images" wrapped metanodes use the KNIME Streaming functionality to convert the input files into KNIME image cells that can be used by the DL4J Learner and Predictor. The "LeNet" metanode (taken from the Node Repository) is a variant of the originally described LeNet convolutional neural network.
This workflow shows basic concepts of the KNIME Deeplearning4J Integration.
This workflow shows an example of the View of the DL4J Feedforward Leaner nodes.
This workflow shows how to create an MLP with a softmax layer for classification.
This workflow shows how to create an MLP with a softmax layer for image classification.
This workflow shows how to create a simple convolutional network and use it for image classification.
This example shows how to train a Word Vector model as well as some properties of the resulting vectors.
This example shows how to transform a document into a vector using a word vector model and using these vectors for classification.
This example shows how to perform sentiment classification using word vectors.
This workflow shows how to do anomaly detection of the MNIST dataset using a convolutional network.