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.
Here is a descriptive list of the key features of this tool; you will find the main topics of the machine learning field here:
- Deep learning with CNNs (for classification and regression) and autoencoders (for feature learning)
- Transfer learning with pre-trained CNNs models and models from the Caffe model zoo
- Training and inference with CPUs or multi-GPUs on desktops, clusters, and clouds
- Unsupervised learning algorithms, including self-organizing maps and competitive layers
In the following screenshot, the product capabilities of the Neural Networks Toolbox are shown, extracted from the MathWorks site:
Figure 1.21: Product capabilities of the Neural Networks Toolbox
- Supervised learning algorithms, including multilayer, radial basis, Learning Vector Quantization (LVQ), time-delay, nonlinear autoregressive (NARX), and Recurrent Neural Network (RNNs)
- Apps for data fitting, pattern recognition, and clustering
- Preprocessing, postprocessing, and network visualization for improving training efficiency and assessing network performance
Note
For a more comprehensive overview of the Neural Network Toolbox's capabilities, you can connect to the manufacturer's website at the following link: https://www.mathworks.com/products/ neural-network.html.