Main Content

Deep Learning in MATLAB

What Is Deep Learning?

Deep learning is a branch of machine learning that teaches computers to do what comes naturally to humans: learn from experience. Deep learning uses neural networks to learn useful representations of features directly from data. Neural networks combine multiple nonlinear processing layers, using simple elements operating in parallel and inspired by biological nervous systems. Deep learning models can achieve state-of-the-art accuracy in object classification, sometimes exceeding human-level performance.

Deep Learning Toolbox™ provides simple MATLAB® commands for creating and interconnecting the layers of a deep neural network. Examples and pretrained networks make it easy to use MATLAB for deep learning, even without knowledge of advanced computer vision algorithms or neural networks.

For a free hands-on introduction to practical deep learning methods, see Deep Learning Onramp. To quickly get started deep learning, see Try Deep Learning in 10 Lines of MATLAB Code.

Start Deep Learning Faster Using Transfer Learning

Transfer learning is commonly used in deep learning applications. You can take a pretrained network and use it as a starting point to learn a new task. Fine-tuning a network with transfer learning is much faster and easier than training from scratch. You can quickly make the network learn a new task using a smaller number of training images. The advantage of transfer learning is that the pretrained network has already learned a rich set of features that can be applied to a wide range of other similar tasks. For an interactive example, see Transfer Learning with Deep Network Designer. For a programmatic example, see Train Deep Learning Network to Classify New Images.

To choose whether to use a pretrained network or create a new deep network, consider the scenarios in this table.

 Use a Pretrained Network for Transfer LearningCreate a New Deep Network
Training DataHundreds to thousands of labeled data (small)Thousands to millions of labeled data
ComputationModerate computation (GPU optional)Compute intensive (requires GPU for speed)
Training TimeSeconds to minutesDays to weeks for real problems
Model AccuracyGood, depends on the pretrained modelHigh, but can overfit to small data sets

To explore a selection of pretrained networks, use Deep Network Designer.

Deep Learning Workflows

To learn more about deep learning application areas, see Applications.

DomainExample WorkflowLearn More

Image classification, regression, and processing

Image data example

Apply deep learning to image data tasks.

For example, use deep learning for image classification and regression.

Get Started with Transfer Learning

Pretrained Deep Neural Networks

Create Simple Deep Learning Neural Network for Classification

Train Convolutional Neural Network for Regression

Preprocess Images for Deep Learning

Sequences and time series

Time series data example

Apply deep learning to sequence and time series tasks.

For example, use deep learning for sequence classification and time series forecasting.

Sequence Classification Using Deep Learning

Time Series Forecasting Using Deep Learning

Computer vision

Semantic segmentation data example

Apply deep learning to computer vision applications.

For example, use deep learning for semantic segmentation and object detection.

Getting Started with Semantic Segmentation Using Deep Learning (Computer Vision Toolbox)

Recognition, Object Detection, and Semantic Segmentation (Computer Vision Toolbox)

Audio processing

Audio data example

Apply deep learning to audio and speech processing applications.

For example, use deep learning for speaker identification, speech command recognition, and acoustic scene recognition.

Audio Processing

Deep Learning for Audio Applications (Audio Toolbox)

Automated driving

Automated driving data example

Apply deep learning to automated driving applications.

For example, use deep learning for vehicle detection and semantic segmentation.

Automated Driving

Train a Deep Learning Vehicle Detector

Signal processing

Signal processing data example

Apply deep learning to signal processing applications.

For example, use deep learning for waveform segmentation, signal classification, and denoising speech signals.

Signal Processing

Classify Time Series Using Wavelet Analysis and Deep Learning

Wireless communications

Wireless communications data example

Apply deep learning to wireless communications systems.

For example, use deep learning for positioning, spectrum sensing, autoencoder design, and digital predistortion (DPD).

Wireless Communications

Spectrum Sensing with Deep Learning to Identify 5G and LTE Signals

Three-Dimensional Indoor Positioning with 802.11az Fingerprinting and Deep Learning (WLAN Toolbox)

Reinforcement learning

Reinforcement learning data example

Train deep neural network agents by interacting with an unknown dynamic environment.

For example, use reinforcement learning to train policies to implement controllers and decision-making algorithms for complex applications such as resource allocation, robotics, and autonomous systems.

Reinforcement Learning

Computational finance

Computational finance data example

Apply deep learning to financial workflows.

For example, use deep learning for applications including instrument pricing, trading, and risk management.

Computational Finance

Compare Deep Learning Networks for Credit Default Prediction

Lidar processing

Lidar processing data example

Apply deep learning algorithms to process lidar point cloud data.

For example, use deep learning for semantic segmentation, object detection on 3-D organized lidar point cloud data.

Lidar Processing

Aerial Lidar Semantic Segmentation Using PointNet++ Deep Learning

Lidar 3-D Object Detection Using PointPillars Deep Learning

Text analytics

Text analytics data example

Apply deep learning algorithms to text analytics applications.

For example, use deep learning for text classification, language translation, and text generation.

Text Analytics

Classify Text Data Using Deep Learning

Predictive maintenance

Predictive maintenance data example

Apply deep learning to predictive maintenance applications.

For example, use deep learning for fault detection and remaining useful life estimation.

Predictive Maintenance

Chemical Process Fault Detection Using Deep Learning

Deep Learning Apps

Process data, visualize and train networks, track experiments, and quantize networks interactively using apps.

You can process your data before training using apps to label ground truth data. For more information on choosing a labeling app, see Choose an App to Label Ground Truth Data.

NameDescriptionLearn More
Deep Network Designer

Deep Network Designer

Build, visualize, edit, and train deep learning networks.

Transfer Learning with Deep Network Designer

Train Network for Time Series Forecasting Using Deep Network Designer

Experiment Manager

Experiment Manager

Create deep learning experiments to train networks under multiple initial conditions and compare the results.

Create a Deep Learning Experiment for Classification

Create a Deep Learning Experiment for Regression

Deep Network Quantizer

Deep Network Quantizer

Reduce the memory requirement of a deep neural network by quantizing weights, biases, and activations of convolution layers to 8-bit scaled integer data types.

Quantization of Deep Neural Networks

Reinforcement Learning Designer (Reinforcement Learning Toolbox)

Reinforcement Learning Designer

Design, train, and simulate reinforcement learning agents.Design and Train Agent Using Reinforcement Learning Designer (Reinforcement Learning Toolbox)
Image Labeler (Computer Vision Toolbox)

Image Labeler

Label ground truth data in a collection of images.

Get Started with the Image Labeler (Computer Vision Toolbox)

Video Labeler (Computer Vision Toolbox)

Video Labeler

Label ground truth data in a video, in an image sequence, or from a custom data source reader.

Get Started with the Video Labeler (Computer Vision Toolbox)

Ground Truth Labeler (Automated Driving Toolbox)

Ground Truth Labeler

Label ground truth data in multiple videos, image sequences, or lidar point clouds.

Get Started with Ground Truth Labelling (Automated Driving Toolbox)

Lidar Labeler (Lidar Toolbox)

Lidar Labeler

Label objects in a point cloud or a point cloud sequence. The app reads point cloud data from PLY, PCAP, LAS, LAZ, ROS and PCD files.

Get Started with the Lidar Labeler (Lidar Toolbox)

Signal Labeler (Signal Processing Toolbox)

Signal Labeler

Label signals for analysis or for use in machine learning and deep learning applications.

Using Signal Labeler App (Signal Processing Toolbox)

Train Classifiers Using Features Extracted from Pretrained Networks

Feature extraction allows you to use the power of pretrained networks without investing time and effort into training. Feature extraction can be the fastest way to use deep learning. You extract learned features from a pretrained network, and use those features to train a classifier, for example, a support vector machine (SVM — requires Statistics and Machine Learning Toolbox™). For example, if an SVM trained using alexnet can achieve >90% accuracy on your training and validation set, then fine-tuning with transfer learning might not be worth the effort to gain some extra accuracy. If you perform fine-tuning on a small dataset, then you also risk overfitting. If the SVM cannot achieve good enough accuracy for your application, then fine-tuning is worth the effort to seek higher accuracy.

For an example, see Extract Image Features Using Pretrained Network.

Deep Learning with Big Data on CPUs, GPUs, in Parallel, and on the Cloud

Training deep networks is computationally intensive and can take many hours of computing time; however, neural networks are inherently parallel algorithms. You can use Parallel Computing Toolbox™ to take advantage of this parallelism by running in parallel using high-performance GPUs and computer clusters. To learn more about deep learning in parallel, in the cloud, or using a GPU, see Scale Up Deep Learning in Parallel, on GPUs, and in the Cloud.

Accelerating training in the cloud with Parallel Computing Toolbox.

Datastores in MATLAB® are a convenient way of working with and representing collections of data that are too large to fit in memory at one time. To learn more about deep learning with large data sets, see Deep Learning with Big Data.

Deep Learning Using Simulink

Implement deep learning functionality in Simulink® models by using blocks from the Deep Neural Networks block library, included in the Deep Learning Toolbox™, or by using the Deep Learning Object Detector block from the Analysis & Enhancement block library included in the Computer Vision Toolbox™.

For more information, see Deep Learning with Simulink.

BlockDescription

Image Classifier

Classify data using a trained deep learning neural network

Predict

Predict responses using a trained deep learning neural network

Stateful Classify

Classify data using a trained deep learning recurrent neural network

Stateful Predict

Predict responses using a trained recurrent neural network

Deep Learning Object Detector (Computer Vision Toolbox)

Detect objects using trained deep learning object detector

Deep Learning Interpretability

Deep learning networks are often described as "black boxes" because the reason that a network makes a certain decision is not always obvious. You can use interpretability techniques to translate network behavior into output that a person can interpret. This interpretable output can then answer questions about the predictions of a network.

The Deep Learning Toolbox provides several deep learning visualization methods to help you investigate and understand network behavior. For example, gradCAM, occlusionSensitivity, and imageLIME. For more information, see Deep Learning Visualization Methods.

Deep learning interpretability and visualization methods applied to an image of a dog.

Deep Learning Customization

You can train and customize a deep learning model in various ways. For example, you can build a network using built-in layers or define custom layers. You can then train your network using the built-in training functions trainnet and trainNetwork, or define a deep learning model as a function and use a custom training loop. For help deciding which method to use, consult the following table.

MethodUse CaseLearn More
Built-in training and layersSuitable for most deep learning tasks.

Custom layersIf Deep Learning Toolbox does not provide the layer you need for your task, then you can create a custom layer.
Custom training loopIf you need additional customization, you can build and train your network using a custom training loop.

For more information, see Train Deep Learning Model in MATLAB.

Deep Learning Import and Export

You can import neural networks and layer graphs from TensorFlow™ 2, TensorFlow-Keras, PyTorch®, and the ONNX™ (Open Neural Network Exchange) model format. You can also export Deep Learning Toolbox neural networks and layer graphs to TensorFlow 2 and the ONNX model format.

Import Functions

External Deep Learning Platform and Model FormatImport Model as dlnetwork
TensorFlow neural network or TensorFlow-Keras neural network in SavedModel formatimportNetworkFromTensorFlow
traced PyTorch model in .pt fileimportNetworkFromPyTorch
Neural network in ONNX model formatimportNetworkFromONNX

The importNetworkFromTensorFlow, importNetworkFromPyTorch, and importNetworkFromONNX functions create automatically generated custom layers when you import a model with TensorFlow layers, PyTorch layers, or ONNX operators that the functions cannot convert to built-in MATLAB layers. The functions save the automatically generated custom layers to a package in the current folder. For more information, see Autogenerated Custom Layers.

Export Functions

Export Neural Network or Layer GraphExternal Deep Learning Platform and Model Format
exportNetworkToTensorFlowTensorFlow 2 model in Python® package
exportONNXNetworkONNX model format

The exportNetworkToTensorFlow function saves a Deep Learning Toolbox neural network or layer graph as a TensorFlow model in a Python package. For more information on how to load the exported model and save it in a standard TensorFlow format, see Load Exported TensorFlow Model and Save Exported TensorFlow Model in Standard Format.

By using ONNX as an intermediate format, you can interoperate with other deep learning frameworks that support ONNX model export or import.

Related Topics