Deep Learning

 

MATLAB for Deep Learning

Design, build, and visualize convolutional neural networks

With just a few lines of MATLAB® code, you can build deep learning models without having to be an expert. Explore how MATLAB can help you perform deep learning tasks.

  • MATLAB is fast: Run deployed models up to 4x faster than TensorFlow and up to 14x faster than Caffe.
  • Easily access the latest models, including GoogLeNet, VGG-16, VGG-19, and AlexNet.
  • Use NVIDIA GPUs for your GPU programming: Accelerate training using multiple GPUs, the cloud, or clusters.
  • Use functions and tools to visualize intermediate results and debug deep learning models.
  • Automate ground-truth labeling using apps.
  • Work with models from Caffe and TensorFlow.

Want a Demonstration?

Learn how to perform deep learning using MATLAB, a webcam, and a pretrained neural network to identify objects in your surroundings. Watch the video and follow along with the code:

clear
camera = webcam;                           % Connect to camera
nnet = alexnet;                            % Load neural net
while true  
    picture = camera.snapshot;             % Take picture
    picture = imresize(picture,[227,227]); % Resize
    label = classify(nnet, picture);       % Classify 
    image(picture);                        % Show picture
    title(char(label));                    % Show label
    drawnow;   
end

 

Interested in learning more? Get a trial of the products you’ll need and download the AlexNet support package.

Explore Examples

Go from basic tasks to more advanced maneuvers by walking through interactive examples and tutorials.

Get a Free Trial

30 days of exploration at your fingertips.

Have Questions?

Talk to a deep learning expert.