Neural Networks

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.

ReferenceReference

Automated Machine Learning

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

Net Representation

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

Net Operations

NetTrain train parameters in any net from examples

NetInitialize randomly initialize parameters for a network

Prebuilt Material

ResourceData access to prebuilt networks, training data, etc.

Basic Layers

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

Loss Layers

MeanSquaredLossLayer  ▪  MeanAbsoluteLossLayer  ▪  CrossEntropyLossLayer

Structure-Changing Layers

CatenateLayer  ▪  FlattenLayer  ▪  ReshapeLayer  ▪  SummationLayer

Convolutional Layers

ConvolutionLayer  ▪  DeconvolutionLayer  ▪  PoolingLayer

Training Optimization Layers

BatchNormalizationLayer  ▪  DropoutLayer

Encoding & Decoding

NetEncoder convert images, categories, etc. to net-compatible numerical arrays

NetDecoder interpret net-generated numerical arrays as images, probabilities, etc.

Activation Functions

Ramp rectified linear (ReLU)

Tanh  ▪  LogisticSigmoid

Importing & Exporting

"WLNet" Wolfram Language Net representation format

Import  ▪  Export

Managing Data & Training

ClassifierMeasurements measure accuracy, recall, etc. of a classifier net

DeleteMissing remove missing data before training