The Wolfram Language has state-of-the-art capabilities for the construction, training, and deployment of neural network machine learning systems. Many standard layer types are available and are assembled symbolically into a network, which can then immediately be trained and deployed on available CPUs and GPUs.
Classify — automatic training and classification using neural networks and other methods
Predict — automatic training and data prediction
FeatureExtraction — automatic feature extraction from image, text, numeric, etc. data
ImageIdentify — fully trained image identification for common objects
NetGraph — symbolic representation of trained or untrained net graphs to be applied to data
NetChain — symbolic representation of a simple chain of net layers
NetPort — symbolic representation of a named input or output port for a layer
NetExtract — extract properties and weights etc. from nets
NetTrain — train parameters in any net from examples
NetInitialize — randomly initialize parameters for a network
ResourceData — access to prebuilt networks, training data, etc.
DotPlusLayer — trainable layer with dense connections computing
ElementwiseLayer — apply a specified function to each element in a tensor
TotalLayer — layer adding corresponding elements of multiple tensors
SoftmaxLayer — layer globally normalizing elements to the unit interval
EmbeddingLayer — trainable layer for embedding integers into continuous vector spaces
NetEncoder — convert images, categories, etc. to net-compatible numerical arrays
NetDecoder — interpret net-generated numerical arrays as images, probabilities, etc.
Ramp — rectified linear (ReLU)
"WLNet" — Wolfram Language Net representation format
ClassifierMeasurements — measure accuracy, recall, etc. of a classifier net
DeleteMissing — remove missing data before training