Deep Learning

What’s New in MATLAB for Deep Learning?

MATLAB makes deep learning easy and accessible for everyone, even if you’re not an expert. Check out the latest features for designing and building your own models, network training and visualization, and deployment.

Data Preparation and Labeling

  • App to label pixels and regions for semantic segmentation and object detection
  • Automate ground-truth labeling using automation API

Network Architectures

  • Directed Acyclic Graph (DAG) networks to represent complex architectures
  • Long short-term memory (LSTM) networks for prediction and classification on time-series, text, and signal data
  • Classification of individual pixels using semantic segmentation
  • New Regression and bi-directional LSTMs for continuous, time-series outputs
  • Custom layers support: Define new layers and specify loss functions for classification and regression output layers
  • New Automatic validation of custom layers to check for data size and type consistency

Access the Latest Pretrained Models

  • New ONNX model converter
  • New Inception-ResNet-v2, SqueezeNet
  • TensorFlow-Keras model importer
  • Import models from Caffe (including Caffe Model Zoo)
  • Inception-v3, ResNet-50, ResNet-101, GoogLeNet, VGG-16, VGG-19, and AlexNet

Network Training

  • Automatically validate network performance, and stop training when the validation metrics stop improving
  • Perform hyperparameter tuning using Bayesian optimization
  • New Additional optimizers for training: ADAM & RMSprop
  • New Train DAG networks in parallel and on multiple GPUs

Debugging and Visualization

  • New DAG activations: Visualize intermediate activations for networks like Inception-ResNet-v2, ResNet-50, ResNet-101, GoogLeNet and Inception-v3
  • New Plot and analyze your network using the Network Analyzer app
  • Monitor training progress with plots for accuracy, loss, and validation metrics

Deployment

  • Automatically convert trained deep learning models in MATLAB to CUDA using GPU Coder
  • New Integrate the generated CUDA code with NVIDIA TensorRT
  • New Support for DAG networks including GoogLeNet, ResNet-50, ResNet-101, and SegNet
  • New Generate code from trained deep learning models for Intel Xeon and ARM Cortex-A processors

Get a Free Trial

30 days of exploration at your fingertips.

Have Questions?

Talk to a deep learning expert.