时间序列和序列数据网络
R2026b将针对时间序列分类、回归和预测任务训练的网络部署到目标 FPGA 和 SoC 板
您可以通过使用长短期记忆 (LSTM) 网络来训练和部署网络，以执行时间序列分类、回归和预测任务。LSTM 是一种循环神经网络 (RNN)，可以学习序列数据的时间步之间的长期依赖关系。了解：
对 LSTM 网络的支持。
Deep Learning HDL Toolbox™ 如何编译网络中的 LSTM 层。
如何将 LSTM 网络部署到目标 FPGA 和 SoC 板，然后使用 Deep Learning HDL Toolbox 和 MATLAB® 从网络检索预测结果。
函数
| Configure deployment workflow for deep learning neural network |
| Configure interface to target board for workflow deployment |
主题
- Support for Long Short-Term Memory Networks (Deep Learning HDL Toolbox)
Learn about Deep Learning HDL Toolbox support for long short-term memory (LSTM) networks.
精选示例
Run Sequence-to-Sequence Classification Networks with Projected Layers on FPGA
Improve network performance by using a projected layer network.
Run Sequence-to-Sequence Classification on Intel FPGA
Create, compile, and deploy a long short-term memory (LSTM) network trained on accelerometer data from human movement by using the HDL Coder™ Support Package for Intel® FPGA and SoC Devices. Use the deployed network to classify human activity based on sequence input data. Use MATLAB® to retrieve the prediction results from the target device.
