matlab神经网络1：功能&特色

1.matlab的神经网络工具箱能做什么？

Neural Network Toolbox （神经网络工具箱）provides algorithms, pretrained models, and apps to create,train, visualize, and simulate both shallow and deep neural networks. You can perform classification,regression,
clustering, dimensionality reduction, time-series forecasting,and dynamic system modeling and control.
Deep learning networks （深度神经网络工具箱） include convolutional neural networks (ConvNets, CNNs),directed acyclic graph (DAG) network topologies, and autoencoders for image
classification, regression, and feature learning. For time-series classification and prediction, the toolbox provides long short-term memory (LSTM) deep learning networks.You can visualize intermediate layers and activations,
modify network architecture, andmonitor training progress.

2.关键的特色有哪些？

Deep learning with convolutional neural networks (CNNs), long short-term memory(LSTM) networks (for time series classification), and autoencoders (for featurelearning，特征学习)
Directed acyclic graph (DAG) networks for deep learning with complex architectures 
Transfer learning with pretrained CNN models (GoogLeNet, AlexNet, VGG16, and VGG19) and models from the Caffe Model Zoo
Unsupervised learning algorithms, including self-organizing maps and competitive layers
Supervised learning algorithms, including multilayer, radial basis, learning vector quantization (LVQ), time-delay, nonlinear autoregressive (NARX), and recurrent neural network (RNN)

3.参考资料

1.Neural Network Toolbox Getting Started Guide
2.Neural Network Toolbox User’s Guide
3.Neural Network Toolbox Reference
4.Neural Network Toolbox Release Notes