Reconnaissance de patterns

Entraîner un réseau de neurones pour généraliser des exemples d’entrées et leurs classes, entraîner des autoencodeurs

Applications

Résoudre un problème de reconnaissance de formes avec des réseaux feedforward à deux couches

Autoencoder Autoencoder class

`nprtool`	Ouvrir l’application Neural Net Pattern Recognition
`view`	Afficher un réseau de neurones peu profond

`trainAutoencoder`	Train an autoencoder
`trainSoftmaxLayer`	Train a softmax layer for classification
`decode`	Decode encoded data
`encode`	Encode input data
`predict`	Reconstruct the inputs using trained autoencoder
`stack`	Stack encoders from several autoencoders together
`network`	Convert `Autoencoder` object into `network` object

`patternnet`	Générer un réseau de reconnaissance de formes
`lvqnet`	Learning vector quantization neural network

`train`	Entraîner un réseau de neurones peu profond
`trainlm`	Levenberg-Marquardt backpropagation
`trainbr`	Bayesian regularization backpropagation
`trainscg`	Scaled conjugate gradient backpropagation
`trainrp`	Resilient backpropagation
`mse`	Fonction de performance d’erreur quadratique moyenne normalisée
`roc`	Receiver operating characteristic
`plotconfusion`	Plot classification confusion matrix
`ploterrhist`	Plot error histogram
`plotperform`	Tracer les performances d’un réseau
`plotregression`	Tracer une régression linéaire
`plotroc`	Tracer la fonction d’efficacité d’un récepteur
`plottrainstate`	Tracer les valeurs d'un état de l’apprentissage
`crossentropy`	Neural network performance
`genFunction`	Generate MATLAB function for simulating shallow neural network

Reconnaissance de formes avec un réseau de neurones peu profond
Utilisez un réseau de neurones peu profond pour reconnaître des formes ou patterns.
Deploy Shallow Neural Network Functions
Simulate and deploy trained shallow neural networks using MATLAB^® tools.
Deploy Training of Shallow Neural Networks
Learn how to deploy training of shallow neural networks.

Shallow Neural Networks with Parallel and GPU Computing
Use parallel and distributed computing to speed up neural network training and simulation and handle large data.
Automatically Save Checkpoints During Neural Network Training
Save intermediate results to protect the value of long training runs.

Choose Neural Network Input-Output Processing Functions
Preprocess inputs and targets for more efficient training.
Configure Shallow Neural Network Inputs and Outputs
Learn how to manually configure the network before training using the configure function.
Divide Data for Optimal Neural Network Training
Use functions to divide the data into training, validation, and test sets.
Choose a Multilayer Neural Network Training Function
Comparison of training algorithms on different problem types.
Improve Shallow Neural Network Generalization and Avoid Overfitting
Learn methods to improve generalization and prevent overfitting.
Train Neural Networks with Error Weights
Learn how to use error weighting when training neural networks.
Normalize Errors of Multiple Outputs
Learn how to fit output elements with different ranges of values.

Crab Classification
This example illustrates using a neural network as a classifier to identify the sex of crabs from physical dimensions of the crab.
Wine Classification
This example illustrates how a pattern recognition neural network can classify wines by winery based on its chemical characteristics.
Cancer Detection
This example shows how to train a neural network to detect cancer using mass spectrometry data on protein profiles.
Character Recognition
This example illustrates how to train a neural network to perform simple character recognition.

Train Stacked Autoencoders for Image Classification
This example shows how to train stacked autoencoders to classify images of digits.

Workflow for Neural Network Design
Learn the primary steps in a neural network design process.
Four Levels of Neural Network Design
Learn the different levels of using neural network functionality.
Réseaux de neurones peu profonds multicouches et apprentissage par rétropropagation
Workflow pour le design d’un réseau de neurones feedforward peu profond multicouche pour l'ajustement de fonction et la reconnaissance de formes.
Multilayer Shallow Neural Network Architecture
Learn the architecture of a multilayer shallow neural network.
Understanding Shallow Network Data Structures
Learn how the format of input data structures affects the simulation of networks.
Exemples de jeux de données pour les réseaux de neurones peu profonds
Liste d’exemples de jeux de données à utiliser pour s’entraîner sur les réseaux de neurones peu profonds.
Neural Network Object Properties
Learn properties that define the basic features of a network.
Neural Network Subobject Properties
Learn properties that define network details such as inputs, layers, outputs, targets, biases, and weights.