Deep Learning Toolbox provides a framework for designing and implementing deep neural networks with algorithms, pretrained models, and apps. You can use convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data. You can build network architectures such as generative adversarial networks (GANs) and Siamese networks using automatic differentiation, custom training loops, and shared weights. With the Deep Network Designer app, you can design, analyze, and train networks graphically.
The Experiment Manager app helps you manage multiple deep learning experiments, keep track of training parameters, analyze results, and compare code from different experiments. You can visualize layer activations and graphically monitor training progress. You can exchange models with TensorFlow and PyTorch through the ONNX format and import models from TensorFlow-Keras and Caffe.
The toolbox supports transfer learning with DarkNet-53, ResNet-50, NASNet, SqueezeNet and many other pretrained models. You can speed up training on a single- or multiple-GPU workstation (with Parallel Computing Toolbox), or scale up to clusters and clouds, including NVIDIA GPU Cloud and Amazon EC2 GPU instances (with MATLAB Parallel Server).
ANNs are a computational model used in computer science, built on a large series of simple neural units, called artificial neurons, which draw inspiration from the behavior observed in the axons of a human brain. Each neural unit is connected with many others, and such link defines the activation status of the adjacent neural units. Every single neural unit performs calculations using the summation function. The models based on ANNs are self-learning and training, rather than explicitly programmed, which his is particularly suitable in cases where the solution function is hard to express in a traditional computer program.
The Neural Network Toolbox provides algorithms, pre-trained models, and apps to create, train, visualize, and simulate neural networks with one hidden layer (called shallow neural network) and neural networks with several hidden layers (called deep neural networks).
Through the use of the tools offered, we can perform classification, regression, clustering, dimensionality reduction, time series forecasting, and dynamic system modeling and control. Deep learning networks include convolutional neural networks (CNNs) and autoencoders for image classification, regression, and feature learning. For training sets of moderated sized, we can quickly apply deep learning by performing transfer learning with pre-trained deep networks. To make working on large amounts of data faster, we can use the Parallel Computing Toolbox (another MATLAB toolbox) to distribute computations and data across multicore processors and GPUs on the desktop, and we can scale up to clusters and clouds with MATLAB Distributed Computing Server.