Esta página es para la versión anterior. La página correspondiente en inglés ha sido eliminada en la versión actual.
Deep Learning Toolbox Funciones - Lista alfabética
A
AcceleratedFunction | Accelerated deep learning function (desde R2021a) |
accuracyMetric | Deep learning accuracy metric (desde R2023b) |
activations | (No recomendado) Calcular las activaciones de las capas de una red de deep learning |
adamupdate | Update parameters using adaptive moment estimation (Adam) (desde R2019b) |
adapt | Adaptar una red neuronal a los datos mientras se simula |
adaptiveAveragePooling2dLayer | Adaptive average pooling 2-D layer (desde R2024a) |
adaptwb | Adaptar una red con reglas de aprendizaje de pesos y sesgos |
adddelay | Add delay to neural network response |
addInputLayer | Add input layer to network (desde R2022b) |
additionLayer | Capa de suma |
addLayers | Añadir capas a una red neuronal |
addMetrics | Compute additional classification performance metrics (desde R2022b) |
addParameter | Add parameter to ONNXParameters object (desde R2020b) |
alexnet | (No recomendado) Red neuronal convolucional AlexNet |
analyzeNetwork | Analyze deep learning network architecture |
assembleNetwork | (No recomendado) Ensamblar una red de deep learning a partir de capas preentrenadas |
attention | Dot-product attention (desde R2022b) |
attentionLayer | Dot-product attention layer (desde R2024a) |
aucMetric | Deep learning area under ROC curve (AUC) metric (desde R2023b) |
audioDataAugmenter | Augment audio data (desde R2019b) |
audioDatastore | Datastore for collection of audio files |
audioFeatureExtractor | Streamline audio feature extraction (desde R2019b) |
audioPretrainedNetwork | Pretrained audio neural networks (desde R2024a) |
augment | Apply identical random transformations to multiple images |
augmentedImageDatastore | Transformar lotes para aumentar datos de imágenes |
augmentedImageSource | (To be removed) Generate batches of augmented image data |
Autoencoder | Clase de codificador automático |
average | Compute performance metrics for average receiver operating characteristic (ROC) curve in multiclass problem (desde R2022b) |
averagePooling1dLayer | 1-D average pooling layer (desde R2021b) |
averagePooling2dLayer | Average pooling layer |
averagePooling3dLayer | 3-D average pooling layer |
avgpool | Pool data to average values over spatial dimensions (desde R2019b) |
B
BaselineDistributionDiscriminator | Baseline distribution discriminator (desde R2023a) |
batchnorm | Normalize data across all observations for each channel independently (desde R2019b) |
batchNormalizationLayer | Batch normalization layer |
bilstmLayer | Bidirectional long short-term memory (BiLSTM) layer for recurrent neural network (RNN) |
blockedImageDatastore | Datastore for use with blocks from blockedImage
objects (desde R2021a) |
boxdist | Distance between two position vectors |
boxLabelDatastore | Datastore for bounding box label data (desde R2019b) |
bttderiv | Backpropagation through time derivative function |
C
calibrate | Simulate and collect ranges of a deep neural network (desde R2020a) |
cascadeforwardnet | Generar una red neuronal prealimentada en cascada |
catelements | Concatenate neural network data elements |
catsamples | Concatenate neural network data samples |
catsignals | Concatenate neural network data signals |
cattimesteps | Concatenate neural network data timesteps |
cellmat | Crear un arreglo de celdas de matrices |
cellpose | Configure Cellpose model for cell segmentation (desde R2023b) |
checkLayer | Check validity of custom or function layer |
classificationLayer | (No recomendado) Capa de clasificación de salida |
ClassificationOutputLayer | (Not recommended) Classification output layer |
classify | (No recomendado) Clasificar datos con una red neuronal de deep learning entrenada |
classifyAndUpdateState | (Not recommended) Classify data using a trained recurrent neural network and update the network state |
classifySound | Classify sounds in audio signal (desde R2020b) |
clearCache | Clear accelerated deep learning function trace cache (desde R2021a) |
clippedReluLayer | Capa de unidad lineal rectificada (ReLU) recortada |
close | Close training information plot (desde R2023b) |
closeloop | Convertir la retroalimentación de lazo abierto de una red neuronal en una de lazo cerrado |
codegen | Generate C/C++ code from MATLAB code |
coder.DeepLearningConfig | Create deep learning code generation configuration objects |
coder.getDeepLearningLayers | Get the list of layers supported for code generation for a specific deep learning library |
coder.loadDeepLearningNetwork | Load deep learning network model |
coder.loadNetworkDistributionDiscriminator | Load network distribution discriminator for code generation (desde R2023a) |
combine | Combine data from multiple datastores |
CombinedDatastore | Datastore to combine data read from multiple underlying datastores |
combvec | Crear todas las combinaciones de vectores |
compet | Función de transferencia competitiva |
competlayer | Capa competitiva |
compressNetworkUsingProjection | Compress neural network using projection (desde R2022b) |
con2seq | Convertir vectores concurrentes en vectores secuenciales |
concatenationLayer | Capa de concatenación |
concur | Create concurrent bias vectors |
configure | Configurar las entradas y las salidas de la red para adaptarlas mejor a los datos de entrada y los datos objetivo |
confusion | Matriz de confusión de clasificación |
confusionchart | Crear una gráfica de matriz de confusión para un problema de clasificación |
confusionmat | Calcular la matriz de confusión para un problema de clasificación |
connectLayers | Conectar capas en una red neuronal |
convolution1dLayer | Capa convolucional 1D (desde R2021b) |
convolution2dLayer | 2-D convolutional layer |
convolution3dLayer | 3-D convolutional layer |
convwf | Función de peso de convolución |
countlabels | Count number of unique labels (desde R2021a) |
crop2dLayer | 2-D crop layer |
crop3dLayer | 3-D crop layer (desde R2019b) |
crosschannelnorm | Cross channel square-normalize using local responses (desde R2020a) |
crossChannelNormalizationLayer | Channel-wise local response normalization layer |
crossentropy | Cross-entropy loss for classification tasks (desde R2019b) |
crossentropy | Neural network performance |
ctc | Connectionist temporal classification (CTC) loss for unaligned sequence classification (desde R2021a) |
cwtfilterbank | Continuous wavelet transform filter bank |
cwtLayer | Continuous wavelet transform (CWT) layer (desde R2022b) |
cwtmag2sig | Signal reconstruction from CWT magnitude (desde R2023b) |
D
dag2dlnetwork | Convert SeriesNetwork and DAGNetwork to
dlnetwork (desde R2024a) |
DAGNetwork | (No recomendado) Red gráfica acíclica dirigida (DAG) para deep learning |
darknet19 | (Not recommended) DarkNet-19 convolutional neural network (desde R2020a) |
darknet53 | (No recomendado) Red neuronal convolucional DarkNet-53 (desde R2020a) |
decode | Decode encoded data |
deepDreamImage | Visualize network features using deep dream |
deeplabv3plus | Create DeepLab v3+ convolutional neural network for semantic image segmentation (desde R2024a) |
deepSignalAnomalyDetector | Create signal anomaly detector (desde R2023a) |
defaultderiv | Función derivada predeterminada |
densenet201 | (No recomendado) Red neuronal convolucional DenseNet-201 |
depthConcatenationLayer | Capa de concatenación de profundidad |
detect | Detect objects using PointPillars object detector (desde R2021b) |
detectspeechnn | Detect boundaries of speech in audio signal using AI (desde R2023a) |
detectTextCRAFT | Detect texts in images by using CRAFT deep learning model (desde R2022a) |
dims | Etiquetas de dimensión de dlarray (desde R2019b) |
disconnectLayers | Disconnect layers in neural network |
dist | Función de peso de distancia euclidiana |
distdelaynet | Distributed delay network |
distributionScores | Distribution confidence scores (desde R2023a) |
divideblock | Dividir objetivos en tres conjuntos usando bloques de índices |
divideind | Divide targets into three sets using specified indices |
divideint | Dividir objetivos en tres conjuntos usando índices intercalados |
dividerand | Dividir objetivos en tres conjuntos usando índices aleatorios |
dividetrain | Asignar todos los objetivos a un conjunto de entrenamiento |
dlaccelerate | Accelerate deep learning function for custom training loops (desde R2021a) |
dlarray | Arreglo de deep learning para personalización (desde R2019b) |
dlconv | Deep learning convolution (desde R2019b) |
dlcwt | Deep learning continuous wavelet transform (desde R2022b) |
dlfeval | Evaluate deep learning model for custom training loops (desde R2019b) |
dlgradient | Compute gradients for custom training loops using automatic differentiation (desde R2019b) |
dlhdl.Target | Configure interface to target board for workflow deployment (desde R2020b) |
dlhdl.Workflow | Configure deployment workflow for deep learning neural network (desde R2020b) |
dlistft | Deep learning inverse short-time Fourier transform (desde R2024a) |
dlmodwt | Deep learning maximal overlap discrete wavelet transform and multiresolution analysis (desde R2022a) |
dlmtimes | (Not recommended) Batch matrix multiplication for deep learning (desde R2020a) |
dlnetwork | Redes neuronales de deep learning (desde R2019b) |
dlode45 | Deep learning solution of nonstiff ordinary differential equation (ODE) (desde R2021b) |
dlquantizationOptions | Options for quantizing a trained deep neural network (desde R2020a) |
dlquantizer | Quantize a deep neural network to 8-bit scaled integer data types (desde R2020a) |
dlstft | Deep learning short-time Fourier transform (desde R2021a) |
dltranspconv | Deep learning transposed convolution (desde R2019b) |
dlupdate | Update parameters using custom function (desde R2019b) |
doc2sequence | Convert documents to sequences for deep learning |
dotprod | Función de peso de producto de puntos |
drise | Explain object detection network predictions using D-RISE (desde R2024a) |
dropoutLayer | Capa de abandono |
E
edfheader | Create header structure for EDF or EDF+ file (desde R2021a) |
edfinfo | Get information about EDF/EDF+ file (desde R2020b) |
edfread | Leer datos del archivo EDF/EDF+ (desde R2020b) |
edfwrite | Create or modify EDF or EDF+ file (desde R2021a) |
efficientnetb0 | (No recomendado) Red neuronal convolucional EfficientNet-b0 (desde R2020b) |
elliot2sig | Elliot 2 symmetric sigmoid transfer function |
elliotsig | Elliot symmetric sigmoid transfer function |
elmannet | Elman neural network |
eluLayer | Exponential linear unit (ELU) layer |
embed | Embed discrete data (desde R2020b) |
embeddingConcatenationLayer | Embedding concatenation layer (desde R2023b) |
encode | Encode input data |
EnergyDistributionDiscriminator | Energy distribution discriminator (desde R2023a) |
equalizeLayers | Equalize layer parameters of deep neural network (desde R2022b) |
errsurf | Error surface of single-input neuron |
estimateNetworkMetrics | Estimate network metrics for specific layers of a neural network (desde R2022a) |
estimateNetworkOutputBounds | Estimate output bounds of deep learning network (desde R2022b) |
expandLayers | Expand network layers (desde R2024a) |
experiments.Monitor | Update results table and training plots for custom training experiments (desde R2021a) |
exportNetworkToTensorFlow | Export Deep Learning Toolbox network to TensorFlow (desde R2022b) |
exportONNXNetwork | Export network to ONNX model format |
extendts | Extend time series data to given number of timesteps |
extractdata | Extraer datos de dlarray (desde R2019b) |
F
fasterRCNNObjectDetector | Detect objects using Faster R-CNN deep learning detector |
fastFlowAnomalyDetector | Detect anomalies using FastFlow network (desde R2023a) |
fastRCNNObjectDetector | Detect objects using Fast R-CNN deep learning detector |
fastTextWordEmbedding | Pretrained fastText word embedding |
fcddAnomalyDetector | Detect anomalies using fully convolutional data description (FCDD) network for anomaly detection (desde R2022b) |
featureInputLayer | Capa de entrada de características (desde R2020b) |
feedforwardnet | Generar una red neuronal prealimentada |
filenames2labels | Get list of labels from filenames (desde R2022b) |
findchangepts | Find abrupt changes in signal |
finddim | Find dimensions with specified label (desde R2019b) |
findpeaks | Encontrar los máximos locales |
findPlaceholderLayers | Find placeholder layers in network architecture imported from Keras or ONNX |
fitnet | Red neuronal de ajuste de funciones |
fixunknowns | Process data by marking rows with unknown values |
flattenLayer | Capa aplanada |
folders2labels | Get list of labels from folder names (desde R2021a) |
formwb | Formar sesgos y pesos en un único vector |
forward | Compute deep learning network output for training (desde R2019b) |
fpderiv | Enviar hacia adelante la función de derivada |
freezeParameters | Convert learnable network parameters in ONNXParameters to
nonlearnable (desde R2020b) |
fromnndata | Convert data from standard neural network cell array form |
fScoreMetric | Deep learning F-score metric (desde R2023b) |
fullyconnect | Sum all weighted input data and apply a bias (desde R2019b) |
fullyConnectedLayer | Capa totalmente conectada |
functionLayer | Function layer (desde R2021b) |
functionToLayerGraph | (To be removed) Convert deep learning model function to a layer graph (desde R2019b) |
G
gadd | Generalized addition |
gdivide | Generalized division |
gelu | Apply Gaussian error linear unit (GELU) activation (desde R2022b) |
geluLayer | Gaussian error linear unit (GELU) layer (desde R2022b) |
generateFunction | Generate a MATLAB function to run the autoencoder |
generateSimulink | Generate a Simulink model for the autoencoder |
genFunction | Generate MATLAB function for simulating shallow neural network |
gensim | Generar un bloque de Simulink para la simulación de redes neuronales superficiales |
getelements | Get neural network data elements |
getL2Factor | Get L2 regularization factor of layer learnable parameter |
getLayer | Look up a layer by name or path (desde R2024a) |
getLearnRateFactor | Get learn rate factor of layer learnable parameter |
getsamples | Get neural network data samples |
getsignals | Get neural network data signals |
getsiminit | Get Simulink neural network block initial input and layer delays states |
gettimesteps | Get neural network data timesteps |
getwb | Obtener los valores de peso y sesgo de la red como un vector único |
globalAveragePooling1dLayer | 1-D global average pooling layer (desde R2021b) |
globalAveragePooling2dLayer | 2-D global average pooling layer (desde R2019b) |
globalAveragePooling3dLayer | 3-D global average pooling layer (desde R2019b) |
globalMaxPooling1dLayer | 1-D global max pooling layer (desde R2021b) |
globalMaxPooling2dLayer | Global max pooling layer (desde R2020a) |
globalMaxPooling3dLayer | 3-D global max pooling layer (desde R2020a) |
gmultiply | Multiplicación generalizada |
gnegate | Negación generalizada |
googlenet | (No recomendado) Red neuronal convolucional GoogLeNet |
gpu2nndata | Reformat neural data back from GPU |
gradCAM | Explain network predictions using Grad-CAM (desde R2021a) |
gridtop | Grid layer topology function |
groupedConvolution2dLayer | 2-D grouped convolutional layer |
groupLayers | Group layers into network layers (desde R2024a) |
groupnorm | Normalize data across grouped subsets of channels for each observation independently (desde R2020b) |
groupNormalizationLayer | Group normalization layer (desde R2020b) |
groupSubPlot | Group metrics in experiment training plot (desde R2021a) |
groupSubPlot | Group metrics in training plot (desde R2022b) |
gru | Gated recurrent unit (desde R2020a) |
gruLayer | Gated recurrent unit (GRU) layer for recurrent neural network (RNN) (desde R2020a) |
gruProjectedLayer | Gated recurrent unit (GRU) projected layer for recurrent neural network (RNN) (desde R2023b) |
gsqrt | Generalized square root |
gsubtract | Resta generalizada |
H
hardlim | Función de transferencia de límite estricto |
hardlims | Función de transferencia de límite estricto simétrica |
hasdata | Determine if minibatchqueue can return mini-batch (desde R2020b) |
HBOSDistributionDiscriminator | HBOS distribution discriminator (desde R2023a) |
hextop | Hexagonal layer topology function |
huber | Huber loss for regression tasks (desde R2021a) |
I
image3dInputLayer | 3-D image input layer |
imageDataAugmenter | Configurar el aumento de datos de imagen |
imageDatastore | Datastore for image data |
imageInputLayer | Capa de entrada de imagen |
imageLIME | Explain network predictions using LIME (desde R2020b) |
imagePretrainedNetwork | Pretrained neural network for images (desde R2024a) |
importCaffeLayers | Import convolutional neural network layers from Caffe |
importCaffeNetwork | Import pretrained convolutional neural network models from Caffe |
importKerasLayers | (To be removed) Import layers from Keras network |
importKerasNetwork | (To be removed) Import pretrained Keras network and weights |
importNetworkFromONNX | Import ONNX network as MATLAB network (desde R2023b) |
importNetworkFromPyTorch | Import PyTorch network as MATLAB network (desde R2022b) |
importNetworkFromTensorFlow | Import TensorFlow network as MATLAB network (desde R2023b) |
importONNXFunction | Import pretrained ONNX network as a function (desde R2020b) |
importONNXLayers | (To be removed) Import layers from ONNX network |
importONNXNetwork | (To be removed) Import pretrained ONNX network |
importTensorFlowLayers | (To be removed) Import layers from TensorFlow network (desde R2021a) |
importTensorFlowNetwork | (To be removed) Import pretrained TensorFlow network (desde R2021a) |
inceptionresnetv2 | (No recomendado) Red neuronal convolucional Inception-ResNet-v2 preentrenada |
inceptionv3 | (No recomendado) Red neuronal convolucional Inception-v3 |
ind2vec | Convertir índices en vectores |
ind2word | Map encoding index to word |
indexing1dLayer | 1-D indexing layer (desde R2023b) |
init | Inicializar una red neuronal |
initcon | Conscience bias initialization function |
initialize | Initialize learnable and state parameters of a
dlnetwork (desde R2021a) |
initlay | Función de inicialización de red de capa a capa |
initlvq | LVQ weight initialization function |
initnw | Nguyen-Widrow layer initialization function |
initwb | By weight and bias layer initialization function |
initzero | Zero weight and bias initialization function |
inputLayer | Input layer (desde R2023b) |
instancenorm | Normalize across each channel for each observation independently (desde R2021a) |
instanceNormalizationLayer | Instance normalization layer (desde R2021a) |
isconfigured | Indicate if network inputs and outputs are configured |
isdlarray | Check if object is dlarray
(desde R2020b) |
isequal | Check equality of neural networks (desde R2021a) |
isequaln | Check equality of neural networks ignoring NaN
values (desde R2021a) |
isInNetworkDistribution | Determine whether data is within the distribution of the network (desde R2023a) |
istftLayer | Inverse short-time Fourier transform layer (desde R2024a) |
isVocabularyWord | Test if word is member of word embedding or encoding |
L
l1loss | L1 loss for regression tasks (desde R2021b) |
l2loss | L2 loss for regression tasks (desde R2021b) |
labeledSignalSet | Create labeled signal set |
Layer | Capa de red para deep learning |
layerGraph | (No recomendado) Gráfica de capas de red de deep learning |
layernorm | Normalize data across all channels for each observation independently (desde R2021a) |
layerNormalizationLayer | Layer normalization layer (desde R2021a) |
layrecnet | Red neuronal recurrente de capas |
lbfgsState | State of limited-memory BFGS (L-BFGS) solver (desde R2023a) |
lbfgsupdate | Update parameters using limited-memory BFGS (L-BFGS) (desde R2023a) |
leakyrelu | Apply leaky rectified linear unit activation (desde R2019b) |
leakyReluLayer | Capa de unidad lineal rectificada (ReLU) con fugas |
learncon | Conscience bias learning function |
learngd | Gradient descent weight and bias learning function |
learngdm | Gradient descent with momentum weight and bias learning function |
learnh | Hebb weight learning rule |
learnhd | Hebb with decay weight learning rule |
learnis | Instar weight learning function |
learnk | Kohonen weight learning function |
learnlv1 | LVQ1 weight learning function |
learnlv2 | LVQ2.1 weight learning function |
learnos | Outstar weight learning function |
learnp | Perceptron weight and bias learning function |
learnpn | Normalized perceptron weight and bias learning function |
learnsom | Self-organizing map weight learning function |
learnsomb | Batch self-organizing map weight learning function |
learnwh | Widrow-Hoff weight/bias learning function |
linearlayer | Crear una capa lineal |
linkdist | Link distance function |
loadTFLiteModel | Load TensorFlow Lite model (desde R2022a) |
logsig | Función de transferencia sigmoide logarítmica |
lstm | Memoria de corto-largo plazo (desde R2019b) |
lstmLayer | Long short-term memory (LSTM) layer for recurrent neural network (RNN) |
lstmProjectedLayer | Long short-term memory (LSTM) projected layer for recurrent neural network (RNN) (desde R2022b) |
lvqnet | Learning vector quantization neural network |
lvqoutputs | LVQ outputs processing function |
M
mae | Función de rendimiento con media de errores absolutos |
mandist | Función de peso de distancia de Manhattan |
mapminmax | Procesar matrices mediante la aplicación de valores mínimos y máximos de filas a [-1 1 ] |
mapstd | Process matrices by mapping each row’s means to 0 and deviations to 1 |
maskrcnn | Detect objects using Mask R-CNN instance segmentation (desde R2021b) |
matlab.io.datastore.BackgroundDispatchable | (Not recommended) Add prefetch reading support to datastore |
matlab.io.datastore.BackgroundDispatchable.readByIndex | (Not recommended) Return observations specified by index from datastore |
matlab.io.datastore.MiniBatchable | Add mini-batch support to datastore |
matlab.io.datastore.MiniBatchable.read | (Not recommended) Read data from custom mini-batch datastore |
matlab.io.datastore.PartitionableByIndex | (Not recommended) Add parallelization support to datastore |
matlab.io.datastore.PartitionableByIndex.partitionByIndex | (Not recommended) Partition datastore according to indices |
maxlinlr | Maximum learning rate for linear layer |
maxpool | Pool data to maximum value (desde R2019b) |
maxPooling1dLayer | 1-D max pooling layer (desde R2021b) |
maxPooling2dLayer | Max pooling layer |
maxPooling3dLayer | 3-D max pooling layer |
maxunpool | Unpool the output of a maximum pooling operation (desde R2019b) |
maxUnpooling2dLayer | Max unpooling layer |
meanabs | Media de los elementos absolutos de una matriz o matrices |
meansqr | Media del cuadrado de los elementos de una matriz o matrices |
midpoint | Función de inicialización de pesos midpoint |
minibatchpredict | Mini-batched neural network prediction (desde R2024a) |
minibatchqueue | Create mini-batches for deep learning (desde R2020b) |
minmax | Intervalos de filas de matrices |
mobilenetv2 | (No recomendado) Red neuronal convolucional MobileNet-v2 |
modwt | Maximal overlap discrete wavelet transform |
modwtLayer | Maximal overlap discrete wavelet transform (MODWT) layer (desde R2022b) |
mse | Error cuadrático medio dividido (desde R2019b) |
mse | Función de rendimiento normalizada de error cuadrático medio |
multiplicationLayer | Multiplication layer (desde R2020b) |
N
narnet | Red neuronal autorregresiva no lineal |
narxnet | Red neuronal autorregresiva no lineal con entrada externa |
nasnetlarge | (No recomendado) Red neuronal convolucional NASNet-Large preentrenada |
nasnetmobile | (No recomendado) Red neuronal convolucional NASNet-Mobile preentrenada |
nctool | Abrir la app Neural Net Clustering |
negdist | Negative distance weight function |
netinv | Función de transferencia inversa |
netprod | Product net input function |
netsum | Sum net input function |
network | Convert Autoencoder object into network object |
network | Crear una red neuronal superficial personalizada |
NetworkAnalysis | Deep learning network analysis information (desde R2024a) |
networkDataLayout | Deep learning network data layout for learnable parameter initialization (desde R2022b) |
networkDistributionDiscriminator | Deep learning distribution discriminator (desde R2023a) |
networkLayer | Network Layer (desde R2024a) |
neuralODELayer | Neural ODE layer (desde R2023b) |
neuronPCA | Principal component analysis of neuron activations (desde R2022b) |
newgrnn | Diseñar una red neuronal de regresión generalizada |
newlind | Design linear layer |
newpnn | Diseñar una red neuronal probabilística |
newrb | Diseñar una red de base radial |
newrbe | Diseñar una red de base radial exacta |
next | Obtener el próximo minilote de datos de minibatchqueue (desde R2020b) |
nftool | Abrir la app Neural Net Fitting |
nncell2mat | Combine neural network cell data into matrix |
nncorr | Cross correlation between neural network time series |
nndata | Create neural network data |
nndata2gpu | Format neural data for efficient GPU training or simulation |
nndata2sim | Convert neural network data to Simulink time series |
nnsize | Number of neural data elements, samples, timesteps, and signals |
nntool | (Eliminado) Abrir Network/Data Manager |
nntraintool | (Eliminada) Herramienta de entrenamiento de redes neuronales |
noloop | Remove neural network open- and closed-loop feedback |
normc | Normalizar columnas de una matriz |
normprod | Normalized dot product weight function |
normr | Normalizar filas de una matriz |
nprtool | Abrir la app Neural Net Pattern Recognition |
ntstool | Abrir la app Neural Net Time Series |
num2deriv | Numeric two-point network derivative function |
num5deriv | Numeric five-point stencil neural network derivative function |
numelements | Number of elements in neural network data |
numfinite | Number of finite values in neural network data |
numnan | Number of NaN values in neural network data |
numsamples | Number of samples in neural network data |
numsignals | Number of signals in neural network data |
numtimesteps | Number of time steps in neural network data |
O
occlusionSensitivity | Explain network predictions by occluding the inputs (desde R2019b) |
ODINDistributionDiscriminator | ODIN distribution discriminator (desde R2023a) |
onehotdecode | Decode probability vectors into class labels (desde R2020b) |
onehotencode | Encode data labels into one-hot vectors (desde R2020b) |
ONNXParameters | Parameters of imported ONNX network for deep learning (desde R2020b) |
openl3Embeddings | Extract OpenL3 feature embeddings (desde R2022a) |
openloop | Convert neural network closed-loop feedback to open loop |
P
paddata | Pad data by adding elements (desde R2023b) |
padsequences | Pad or truncate sequence data to same length (desde R2021a) |
partition | Partition minibatchqueue (desde R2020b) |
partitionByIndex | Partition augmentedImageDatastore according to
indices |
patchCoreAnomalyDetector | Detect anomalies using PatchCore network (desde R2023a) |
patchEmbeddingLayer | Patch embedding layer (desde R2023b) |
patternnet | Generar una red de reconocimiento de patrones |
perceptron | Clasificador binario de una sola capa simple |
perform | Calcular el rendimiento de la red |
pitchnn | Estimate pitch with deep learning neural network (desde R2021a) |
pixelLabelDatastore | Datastore for pixel label data |
PlaceholderLayer | Layer replacing an unsupported Keras or ONNX layer |
plot | Representar una arquitectura de red neuronal |
plot | Plot receiver operating characteristic (ROC) curves and other performance curves (desde R2022b) |
plotconfusion | Representar una matriz de confusión de clasificación |
plotep | Plot weight-bias position on error surface |
ploterrcorr | Plot autocorrelation of error time series |
ploterrhist | Representar un histograma de error |
plotes | Plot error surface of single-input neuron |
plotfit | Representar el ajuste de una función |
plotinerrcorr | Plot input to error time-series cross-correlation |
plotpc | Representar la línea de clasificación en la gráfica de vectores del perceptrón |
plotperform | Representar el rendimiento de la red |
plotpv | Representar ventores de entrada/objetivo del perceptrón |
plotregression | Representar una regresión lineal |
plotresponse | Representar una respuesta de serie de tiempo de red dinámica |
plotroc | Representar la característica de funcionamiento del receptor |
plotsom | Plot self-organizing map |
plotsomhits | Representar los aciertos de muestra de un mapa autoorganizado |
plotsomnc | Representar conexiones vecinas de mapa autoorganizado |
plotsomnd | Representar distancias de vecinas de un mapa autoorganizado |
plotsomplanes | Plot self-organizing map weight planes |
plotsompos | Representar posiciones de pesos de un mapa autoorganizado |
plotsomtop | Representar una topología de mapa autoorganizado |
plottrainstate | Representar valores de estado de entrenamiento |
plotv | (Se eliminará) Representar vectores como líneas desde el origen |
plotvec | Representar vectores con diferentes colores |
plotwb | Plot Hinton diagram of weight and bias values |
plotWeights | Plot a visualization of the weights for the encoder of an autoencoder |
pnormc | Pseudonormalize columns of matrix |
pointnetplusLayers | (Not recommended) Create PointNet++ segmentation network (desde R2021b) |
pointPillarsObjectDetector | PointPillars object detector (desde R2021b) |
posemaskrcnn | Predict object pose using Pose Mask R-CNN pose estimation (desde R2024a) |
positionEmbeddingLayer | Position embedding layer (desde R2023b) |
poslin | Función de transferencia lineal positiva |
precisionMetric | Deep learning precision metric (desde R2023b) |
predict | Compute deep learning network output for inference (desde R2019b) |
predict | (No recomendado) Predecir respuestas usando una red neuronal de deep learning entrenada |
predict | Compute deep learning network output for inference by using a TensorFlow Lite model (desde R2022a) |
predict | Reconstruct the inputs using trained autoencoder |
predictAndUpdateState | (Not recommended) Predict responses using a trained recurrent neural network and update the network state |
preluLayer | Parametrized Rectified Linear Unit (PReLU) layer (desde R2024a) |
preparets | Preparar datos de series de tiempo de entrada y objetivo para simulación o entrenamiento de red |
processpca | Process columns of matrix with principal component analysis |
ProjectedLayer | Compressed neural network layer using projection (desde R2023b) |
prune | Delete neural inputs, layers, and outputs with sizes of zero |
prunedata | Prune data for consistency with pruned network |
purelin | Función de transferencia lineal |
Q
quant | Discretizar valores como múltiplos de cantidad |
quantizationDetails | Display quantization details for a neural network (desde R2022a) |
quantize | Quantize deep neural network (desde R2022a) |
R
radbas | Función de transferencia de base radial |
radbasn | Función de transferencia de base radial normalizada |
randnc | Normalized column weight initialization function |
randnr | Normalized row weight initialization function |
randomPatchExtractionDatastore | Datastore for extracting random 2-D or 3-D random patches from images or pixel label images |
rands | Función de inicialización de peso/sesgo aleatoria simétrica |
randsmall | Small random weight/bias initialization function |
randtop | Random layer topology function |
rcnnObjectDetector | Detect objects using R-CNN deep learning detector |
read | Read data from augmentedImageDatastore |
readByIndex | Read data specified by index from
augmentedImageDatastore |
readWordEmbedding | Read word embedding from file |
recallMetric | Deep learning recall metric (desde R2023b) |
recordMetrics | Record metric values in experiment results table and training plot (desde R2021a) |
recordMetrics | Record metric values for custom training loops (desde R2022b) |
regression | (No recomendado) Realizar una regresión lineal de las salidas de redes superficiales en los objetivos |
regressionLayer | (No recomendado) Capa de salida de regresión |
RegressionOutputLayer | Capa de salida de regresión |
reidentificationNetwork | Re-identification deep learning network for re-identifying and tracking objects (desde R2024a) |
relu | Aplicar la activación de unidad lineal rectificada (desde R2019b) |
reluLayer | Capa de unidad lineal rectificada (ReLU) |
removeconstantrows | Process matrices by removing rows with constant values |
removedelay | Remove delay to neural network’s response |
removeLayers | Remove layers from neural network |
removeParameter | Remove parameter from ONNXParameters object (desde R2020b) |
removerows | Procesar matrices eliminando filas con índices especificados |
replaceLayer | Replace layer in neural network |
reset | Reset minibatchqueue to start of data (desde R2020b) |
resetState | Reset state parameters of neural network |
resize | Resize data by adding or removing elements (desde R2023b) |
resnet101 | (No recomendado) Red neuronal convolucional ResNet-101 |
resnet18 | (No recomendado) Red neuronal convolucional ResNet-18 |
resnet3dLayers | (Not recommended) Create 3-D residual network (desde R2021b) |
resnet3dNetwork | 3-D residual neural network (desde R2024a) |
resnet50 | (No recomendado) Red neuronal convolucional ResNet-50 |
resnetLayers | (Not recommended) Create 2-D residual network (desde R2021b) |
resnetNetwork | 2-D residual neural network (desde R2024a) |
revert | Change network weights and biases to previous initialization values |
risetime | Rise time of positive-going bilevel waveform transitions |
rmseMetric | Deep learning root mean squared error metric (desde R2023b) |
rmspropupdate | Update parameters using root mean squared propagation (RMSProp) (desde R2019b) |
roc | Característica de funcionamiento del receptor |
rocmetrics | Receiver operating characteristic (ROC) curve and performance metrics for binary and multiclass classifiers (desde R2022b) |
S
sae | Sum absolute error performance function |
satlin | Función de transferencia lineal saturada |
satlins | Función de transferencia lineal simétrica saturada |
scalprod | Función de peso de producto de escalar |
scores2label | Convert prediction scores to labels (desde R2024a) |
segmentCells2D | Segment 2-D image using Cellpose (desde R2023b) |
segmentCells3D | Segment 3-D image volume using Cellpose (desde R2023b) |
selfAttentionLayer | Self-attention layer (desde R2023a) |
selforgmap | Mapa autoorganizado |
separateSpeakers | Separate signal by speakers (desde R2023b) |
separatewb | Separar valores de sesgos y pesos de vectores de pesos/sesgos |
seq2con | Convert sequential vectors to concurrent vectors |
sequenceFoldingLayer | (Not recommended) Sequence folding layer |
sequenceInputLayer | Capa de entrada de secuencias |
sequenceUnfoldingLayer | (Not recommended) Sequence unfolding layer |
SeriesNetwork | (No recomendado) Red en serie de deep learning |
setelements | Set neural network data elements |
setL2Factor | Set L2 regularization factor of layer learnable parameter |
setLearnRateFactor | Set learn rate factor of layer learnable parameter |
setsamples | Set neural network data samples |
setsignals | Set neural network data signals |
setsiminit | Set neural network Simulink block initial conditions |
settimesteps | Set neural network data timesteps |
setwb | Set all network weight and bias values with single vector |
sgdmupdate | Update parameters using stochastic gradient descent with momentum (SGDM) (desde R2019b) |
show | Show training information plot (desde R2023b) |
shuffle | Shuffle data in augmentedImageDatastore |
shuffle | Shuffle data in minibatchqueue (desde R2020b) |
shufflenet | (No recomendado) Red neuronal convolucional ShuffleNet preentrenada |
sigmoid | Aplicar la activación sigmoide (desde R2019b) |
sigmoidLayer | Capa sigmoide (desde R2020b) |
signalDatastore | Datastore for collection of signals (desde R2020a) |
signalFrequencyFeatureExtractor | Streamline signal frequency feature extraction (desde R2021b) |
signalLabelDefinition | Create signal label definition |
signalMask | Modify and convert signal masks and extract signal regions of interest (desde R2020b) |
signalTimeFeatureExtractor | Streamline signal time feature extraction (desde R2021a) |
sigrangebinmask | Label signal samples with values within a specified range (desde R2023a) |
sim | Simular una red neuronal |
sim2nndata | Convert Simulink time series to neural network data |
sinusoidalPositionEncodingLayer | Sinusoidal position encoding layer (desde R2023b) |
softmax | Apply softmax activation to channel dimension (desde R2019b) |
softmax | Función de transferencia softmax |
softmaxLayer | Capa softmax |
solov2 | Segment objects using SOLOv2 instance segmentation network (desde R2023b) |
sortClasses | Sort classes of confusion matrix chart |
spatialDropoutLayer | Spatial dropout layer (desde R2024a) |
splitlabels | Find indices to split labels according to specified proportions (desde R2021a) |
squeezenet | (No recomendado) Red neuronal convolucional SqueezeNet |
squeezesegv2Layers | (Not recommended) Create SqueezeSegV2 segmentation network for organized lidar point cloud (desde R2020b) |
srchbac | 1-D minimization using backtracking |
srchbre | 1-D interval location using Brent’s method |
srchcha | 1-D minimization using Charalambous' method |
srchgol | 1-D minimization using golden section search |
srchhyb | 1-D minimization using a hybrid bisection-cubic search |
ssdObjectDetector | Detect objects using SSD deep learning detector (desde R2020a) |
sse | Función de rendimiento con suma de errores cuadráticos |
stack | Stack encoders from several autoencoders together |
staticderiv | Static derivative function |
stft | Transformada de Fourier de tiempo corto |
stftLayer | Short-time Fourier transform layer (desde R2021b) |
stftmag2sig | Signal reconstruction from STFT magnitude (desde R2020b) |
stripdims | Remove dlarray data format (desde R2019b) |
sumabs | Suma de los elementos absolutos de una matriz o matrices |
summary | Imprimir un resumen de la red (desde R2022b) |
sumsqr | Suma de los cuadrados de los elementos de una matriz o matrices |
swishLayer | Swish layer (desde R2021a) |
T
tanhLayer | Capa de tangente hiperbólica (tanh) |
tansig | Función de transferencia sigmoide tangente hiperbólica |
tapdelay | Shift neural network time series data for tap delay |
taylorPrunableNetwork | Network that can be pruned by using first-order Taylor approximation (desde R2022a) |
TFLiteModel | TensorFlow Lite model (desde R2022a) |
timedelaynet | Red neuronal de retardo de tiempo |
tonndata | Convertir los datos al formato de arreglo de celdas de una red neuronal estándar |
train | Entrenar una red neuronal superficial |
trainAutoencoder | Entrenar un codificador automático |
trainb | Batch training with weight and bias learning rules |
trainbfg | BFGS quasi-Newton backpropagation |
trainbr | Retropropagación de regularización bayesiana |
trainbu | Batch unsupervised weight/bias training |
trainc | Cyclical order weight/bias training |
traincgb | Conjugate gradient backpropagation with Powell-Beale restarts |
traincgf | Conjugate gradient backpropagation with Fletcher-Reeves updates |
traincgp | Conjugate gradient backpropagation with Polak-Ribiére updates |
traingd | Retropropagación del gradiente descendente |
traingda | Gradient descent with adaptive learning rate backpropagation |
traingdm | Retropropagación del gradiente descendente con momento |
traingdx | Gradiente descendente con momento (inercia) y retropropagación de la tasa de aprendizaje adaptativo |
TrainingInfo | Neural network training information (desde R2023b) |
trainingOptions | Opciones para entrenar una red neuronal de deep learning |
TrainingOptionsADAM | Training options for Adam optimizer |
TrainingOptionsLBFGS | Training options for limited-memory BFGS (L-BFGS) optimizer (desde R2023b) |
TrainingOptionsRMSProp | Training options for RMSProp optimizer |
TrainingOptionsSGDM | Training options for stochastic gradient descent with momentum |
trainingProgressMonitor | Monitor and plot training progress for deep learning custom training loops (desde R2022b) |
trainlm | Retropropagación Levenberg-Marquardt |
trainnet | Train deep learning neural network (desde R2023b) |
trainNetwork | (No recomendado) Entrenar una red neuronal |
trainoss | One-step secant backpropagation |
trainPointPillarsObjectDetector | Train PointPillars object detector (desde R2021b) |
trainr | Random order incremental training with learning functions |
trainrp | Resilient backpropagation |
trainru | Unsupervised random order weight/bias training |
trains | Sequential order incremental training with learning functions |
trainscg | Retropropagación de gradiente conjugado escalado |
trainSoftmaxLayer | Train a softmax layer for classification |
trainWordEmbedding | Train word embedding |
transform | Transform datastore |
TransformedDatastore | Datastore to transform underlying datastore |
transposedConv1dLayer | Transposed 1-D convolution layer (desde R2022a) |
transposedConv2dLayer | Transposed 2-D convolution layer |
transposedConv3dLayer | Transposed 3-D convolution layer |
TransposedConvolution1DLayer | Transposed 1-D convolution layer (desde R2022a) |
TransposedConvolution2DLayer | Transposed 2-D convolution layer |
TransposedConvolution3DLayer | Transposed 3-D convolution layer |
tribas | Función de transferencia de base triangular |
trimdata | Trim data by removing elements (desde R2023b) |
tritop | Triangle layer topology function |
U
unconfigure | Unconfigure network inputs and outputs |
unet | Create U-Net convolutional neural network for semantic segmentation (desde R2024a) |
unet3d | Create 3-D U-Net convolutional neural network for semantic segmentation of volumetric images (desde R2024a) |
unfreezeParameters | Convert nonlearnable network parameters in ONNXParameters to
learnable (desde R2020b) |
unpackProjectedLayers | Unpack projected layers of neural network (desde R2023b) |
updateInfo | Update information columns in experiment results table (desde R2021a) |
updateInfo | Update information values for custom training loops (desde R2022b) |
updatePrunables | Remove filters from prunable layers based on importance scores (desde R2022a) |
updateScore | Compute and accumulate Taylor-based importance scores for pruning (desde R2022a) |
V
validate | Quantize and validate a deep neural network (desde R2020a) |
vec2ind | Convertir vectores en índices |
vec2word | Map embedding vector to word |
verifyNetworkRobustness | Verify adversarial robustness of deep learning network (desde R2022b) |
vgg16 | (No recomendado) Red neuronal convolucional VGG-16 |
vgg19 | (No recomendado) Red neuronal convolucional VGG-19 |
vggishEmbeddings | Extract VGGish feature embeddings (desde R2022a) |
view | Visualizar una red neuronal superficial |
view | View autoencoder |
visionTransformer | Pretrained vision transformer (ViT) neural network (desde R2023b) |
W
waveletScattering | Wavelet time scattering |
word2ind | Map word to encoding index |
word2vec | Map word to embedding vector |
wordEmbedding | Word embedding model to map words to vectors and back |
wordEmbeddingLayer | Word embedding layer for deep learning neural network |
wordEncoding | Word encoding model to map words to indices and back |
writeWordEmbedding | Write word embedding file |
X
xception | (No recomendado) Red neuronal convolucional Xception |
Y
yolov2ObjectDetector | Detect objects using YOLO v2 object detector |
yolov3ObjectDetector | Detect objects using YOLO v3 object detector (desde R2021a) |
yolov4ObjectDetector | Detect objects using YOLO v4 object detector (desde R2022a) |
yoloxObjectDetector | Detect objects using YOLOX object detector (desde R2023b) |
yscale | Set training plot y-axis scale (linear or logarithmic) (desde R2024a) |