AI 与统计

R2026b

针对机器学习和深度神经网络进行数据准备、设计、仿真和部署

MATLAB^® 让数据科学工作变得轻松，借助其中的工具，您可以访问和预处理数据、构建机器学习和预测模型，以及部署模型。

使用 App 或仅需几行 MATLAB 代码，您就可以将统计、机器学习和深度学习方法应用于您的工作中，以设计算法、准备和标注数据，或生成代码并将其部署到嵌入式系统中。使用专业工具扩展 AI 建模和数据拟合工作流，以用于：

图像、视频、信号、音频和文本等数据类型
计算机视觉、音频和信号处理、文本分析、无线通信和自动驾驶等应用

Workflow for AI from data preparation to modeling to system design and deployment

适用产品: AI 与统计

Statistics and Machine Learning Toolbox

使用统计信息和机器学习来分析数据并为数据建模

主题

AI 基础

MATLAB 中的机器学习 (Statistics and Machine Learning Toolbox)
了解 MATLAB 中用于分类、回归、聚类和深度学习的机器学习功能，包括用来自动进行模型训练和代码生成的 App。
在 MATLAB 中进行深度学习 (Deep Learning Toolbox)
通过使用卷积神经网络进行分类和回归来探索 MATLAB 的深度学习能力，包括预训练网络和迁移学习，以及在 GPU、CPU、集群和云上进行训练。
What Is Reinforcement Learning? (Reinforcement Learning Toolbox)
Reinforcement learning is a goal-directed computational approach where a computer learns to perform a task by interacting with an uncertain dynamic environment.

AI 建模

Train Classification Models in Classification Learner App (Statistics and Machine Learning Toolbox)
Workflow for training, comparing and improving classification models, including automated, manual, and parallel training.
Train Regression Models in Regression Learner App (Statistics and Machine Learning Toolbox)
Workflow for training, comparing and improving regression models, including automated, manual, and parallel training.
使用深度网络设计器构建网络 (Deep Learning Toolbox)
在深度网络设计器中以交互方式构建和编辑深度学习网络。

仿真和部署

使用深度学习进行电池荷电状态估计 (Deep Learning Toolbox)
定义需求、准备数据、训练深度学习网络、验证稳健性、将网络集成到 Simulink 中以及部署模型。 (自 R2024b 起)
Code Generation for Deep Learning Networks (GPU Coder)
Get started with CUDA^® code generation for image classification networks such as ResNet.
Code Generation for Deep Learning Simulink Model That Performs Lane and Vehicle Detection (Embedded Coder)
This example shows how to generate C++ code from a Simulink® model that performs lane and vehicle detection using convolutional neural networks (CNN).

精选示例

Time Series Prediction in Simulink Using Deep Learning Network

Use an LSTM deep learning network inside a Simulink® model to predict the remaining useful life (RUL) of an engine. You include the network inside the Simulink model by using a Stateful Predict block, which predicts the RUL at every simulation step.

(Deep Learning Toolbox)