Create a NetPairEmbeddingOperator that embeds inputs using a NetChain:

Create a NetPairEmbeddingOperator that embeds a pair of length-2 vectors using a randomly initialized NetChain:

Apply the net to a pair of input vectors:

Thread the layer across a batch of input vectors:

Create a NetGraph with one input and output:

Create a NetPairEmbeddingOperator that embeds vectors using a NetGraph:

The embedding network in NetPairEmbeddingOperator[net] can be extracted using NetExtract:

Train a multilayer perceptron to embed a synthetic dataset based only on its topology. First, create the training data on a spiral-like manifold that is dense in the plane:

Create the perceptron:

Use NetPairEmbeddingOperator to define a loss network that measures the performance of the embedding:

Create a generator that will sample pairs of points and associate them with True if their parameterization on the manifold differs by more than Pi:

Train the network, using a generator to sample pairs of points, and classify them as the same if their original parameterization was close:

Extract the embedding from the net:

Plot the 1D embedding learned by the net as a color map:

Learn an embedding of the digits in the MNIST dataset. First, import the data and take only those examples with labels between 0 and 4:

Create a training set by sampling pairs of images and associating them with True if their labels are different and False if their labels are the same:

Define a convolutional network to use as an embedding network:

Construct the pair-embedding net:

Train the network:

Apply the network to a list of pairs of digits to compute their distances under the embedding. Digits with the same label have small distances:

Extract the embedding network:

Compute the embedding of a digit:

Sample 500 digits and group them by their labels:

Compute their embeddings and plot them. Digits with the same label are clustered under the learned embedding:

NetMapOperator can be used to implement NetPairEmbeddingOperator. Create an initialized LinearLayer:

Create NetPairEmbeddingOperator using the linear layer as its embedding net, and evaluate it on an input:

Define a NetGraph with a NetMapOperator that is equivalent to the previous NetPairEmbeddingOperator, and evaluate it on the same input: