Plot and analyze your network using network analyzer, generate CUDA code that integrates with TensorRT, and deploy deep learning networks to Intel and ARM processors.

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.

• MATLAB is fast: Run deployed models up to 7x faster than TensorFlow and up to 4.5x faster than Caffe2.
• Easily access the latest models, including GoogLeNet, VGG-16, VGG-19, AlexNet, ResNet-50, ResNet-101, and Inception-v3.
• Use NVIDIA GPUs for your GPU programming: Accelerate training using multiple GPUs, the cloud, or clusters.
• Use functions and tools to visualize intermediate results and debug deep learning models.
• Automate ground-truth labeling using apps.
• Work with models from Caffe and TensorFlow-Keras.
  
  

Big data smoothing and outlier detection using tall arrays, grouped calculations, and C code generation for additional machine learning classifiers.

Explore the latest MATLAB® functions and features for developing machine learning models, working with big data, and operationalizing analytics to production systems.

Vehicle Dynamics Blockset™ provides fully assembled reference application models that simulate driving maneuvers in a 3D environment. You can use the prebuilt scenes to visualize roads, traffic signs, trees, buildings, and other objects around the vehicle. You can customize the reference models by using your own data or by replacing a subsystem with your own model. The blockset includes a library of components for modeling propulsion, steering, suspension, vehicle bodies, brakes, and tires.

Vehicle Dynamics Blockset provides a standard model architecture that can be used throughout the development process. It supports ride and handling analyses, chassis controls development, software integration testing, and hardware-in-the-loop testing. By integrating vehicle dynamics models with a 3D environment, you can test ADAS and automated driving perception, planning, and control software. These models let you test your vehicle with standard driving maneuvers such as a double lane change or with your own custom scenarios.

Predictive Maintenance Toolbox™ provides tools for labeling data, designing condition indicators, and estimating the remaining useful life (RUL) of a machine. You can analyze and label machine data imported from local files, cloud storage, and distributed file systems. You can also label simulated failure data generated from Simulink® models.

Signal processing and dynamic modeling methods that build on techniques such as spectral analysis and time series analysis let you preprocess data and extract features that can be used to monitor the condition of the machine. To estimate a machine’s time to failure, you can use survival, similarity, and trend-based models to predict the RUL.

The toolbox includes reference examples for motors, gearboxes, batteries, and other machines that can be reused for developing custom predictive maintenance and condition monitoring algorithms.

下载地址