Deep Learning Applications
With just a few lines of MATLAB code, you can incorporate deep learning into your applications whether you’re designing algorithms, preparing and labeling data, or generating code and deploying to embedded systems.
Why MATLAB for Deep Learning?
MATLAB makes it easy to move from deep learning models to real-world artificial intelligence-driven systems.
Use interactive apps to label, crop, and identify important features, and built-in algorithms to help automate the process of labeling.
Train and Evaluate Models
Start with a complete set of algorithms and prebuilt models, then create and modify deep learning models using the Deep Network Designer app.
Test deep learning models by including them into system-level Simulink simulations. Test edge-case scenarios that are difficult to test on hardware. Understand how your deep learning models impact the performance of the overall system.
Deploy Trained Networks
Deploy your trained model on embedded systems, enterprise systems, FPGA devices, or the cloud. Generate code from Intel®, NVIDIA®, and ARM® libraries to create deployable models with high-performance inference speed.
Integrate with Python-Based Frameworks
MATLAB lets you access the latest research from anywhere by importing Tensorflow models and using ONNX capabilities. You can use a library of prebuilt models, including NASNet, SqueezeNet, Inception-v3, and ResNet-101 to get started. Calling Python from MATLAB and vice versa enables you to collaborate with colleagues who are using open source.
AI Applications with MATLAB and Simulink
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.
- Easily access the latest models, including GoogLeNet, VGG-16, VGG-19, AlexNet, ResNet-50, ResNet-101, and Inception-v3.
- Accelerate algorithms on NVIDIA® GPUs, cloud, and datacenter resources without specialized programming.
- Create, modify, and analyze complex deep neural network architectures using MATLAB apps and visualization tools.
- Automate ground-truth labeling of image, video, and audio data using apps.
- Work with models from Caffe and TensorFlow-Keras.
- MATLAB supports ONNX™, so you can collaborate with peers using frameworks like PyTorch and MxNet.
Why Use MATLAB for Deep Learning?
It’s not an either/or choice between MATLAB and Python-based frameworks. MATLAB supports interoperability with open source deep learning frameworks using ONNX import and export capabilities. Use MATLAB tools where it matters most – accessing capabilities and prebuilt functions and apps not available in Python.
Apps for Preprocessing
Get to network training quickly. Preprocess datasets fast with domain-specific apps for audio, video, and image data. Visualize, check, and fix problems before training using the Deep Network Designer app to create complex network architectures or modify pretrained networks for transfer learning.
Deploy deep learning models anywhere including CUDA, C code, enterprise systems, or the cloud. When performance matters, you can generate code that leverages optimized libraries from Intel® (MKL-DNN), NVIDIA (TensorRT, cuDNN), and ARM® (ARM Compute Library) to create deployable models with high-performance inference speed.