DB004229-AI辅助的通信DSP算法与实现（全英文）

研究生课程开设申请表

开课院（系、所）：信息科学与工程学院      

课程申请开设类型： 新开☑    重开□     更名□（请在□内打勾，下同）

一、课程介绍（含教学目标、教学要求等）（300字以内）

本课程面向信息与通信工程专业研究生，系统介绍人工智能技术在通信DSP算法设计与实现中的应用。课程涵盖神经网络、遗传算法等智能优化方法在DSP系统中的建模、优化与硬件实现。教学目标包括：掌握AI辅助的DSP算法理论基础；具备利用智能算法解决信号处理实际问题的能力；培养跨学科融合的创新设计思维。教学要求学生具备数字信号处理、编程及数学基础，通过理论讲授与项目实践相结合的方式，完成算法仿真与硬件实现任务，提升工程研究与系统实现能力。

二、教学大纲（含章节目录）：（可附页）

第一章：绪论（2学时）

1.1 AI赋能新一代DSP与VLSI设计概述

1.2 AI与DSP融合的发展趋势与典型应用场景

1.3系统架构与智能信号处理系统概述

1.4我国在AI-DSP芯片领域的发展现状与挑战

第二章：核心基础回顾与AI工具准备（2学时）

2.1数字信号处理（DSP）基础理论回顾

2.2人工智能基础概念与算法分类

2.3 MATLAB/Python工具链在DSP中的应用

2.4智能算法开发环境搭建与编程基础

第三章：基带信号处理算法回顾（2学时）

3.1传统DSP算法核心概念回顾

3.2信号检测与信道均衡基础

3.3编译码技术与信号恢复方法

3.4传统方法的局限与智能化需求

第四章：AI辅助通信I：智能信号检测与均衡（2学时）

4.1基于神经网络的信号检测算法

4.2智能信道均衡技术

4.3算法仿真与性能分析

4.4案例分析与实现

第五章：AI辅助通信II：智能信道编译码（2学时）

5.1深度学习在信道编译码中的应用

5.2智能编译码器设计与优化

5.3仿真验证与性能评估

5.4与传统方法的对比分析

第六章：AI辅助设计与优化I：智能演化算法（2学时）

6.1遗传算法基本原理

6.2演化策略在DSP硬件优化中的应用

6.3多目标优化与自动架构搜索

6.4案例研究：硬件资源与功耗优化

第七章：AI辅助设计与优化II：硬件电路的智能自动生成（2学时）

7.1智能硬件生成方法与工具概述

7.2基于机器学习的电路设计自动化

7.3生成模型在VLSI设计中的应用

7.4实现案例与性能分析

第八章：AI辅助设计与优化III：自动低比特量化与压缩（2学时）

8.1低比特量化技术概述

8.2智能量化算法设计与实现

8.3神经网络压缩与硬件加速

8.4实际系统中的应用与挑战

第九章：AI-DSP系统的实现架构I（2学时）

9.1 FPGA平台上的智能算法部署

9.2加速器设计与优化

9.3硬件资源管理与调度

9.4案例：实时信号处理系统实现

第十章：AI-DSP系统的实现架构II（2学时）

10.1 ASIC平台上的智能DSP核设计

10.2软硬件协同优化方法

10.3系统级集成与验证

10.4低功耗与高性能设计权衡

第十一章：AI辅助设计与优化IV：自动评估与性能预测（2学时）

11.1性能建模与预测方法

11.2智能算法在系统评估中的应用

11.3自动化测试与验证流程

11.4案例：端到端系统性能优化

第十二章：案例深度研究：端到端的AI通信基带设计（2学时）

12.1智能极化码编译码系统

12.2智能信道估计与自适应调制

12.3系统集成与协同优化

12.4仿真与硬件验证

第十三章：系统级协同优化与验证（2学时）

13.1多目标系统优化方法

13.2验证策略与测试平台构建

13.3实际工程中的挑战与解决方案

13.4案例分析与总结

第十四章：前沿专题I：自动寻找最优DSP硬件架构（2学时）

14.1自动硬件架构搜索技术

14.2强化学习在架构优化中的应用

14.3多模态优化与动态重构

14.4发展趋势与研究展望

第十五章：前沿专题II：极化码智能构造算法（2学时）

15.1极化码基本原理回顾

15.2智能构造与优化算法

15.3在5G/6G系统中的应用

15.4性能分析与未来方向

第十六章：课程总结与展望（2学时）

16.1课程内容回顾与知识体系梳理

16.2 AI-DSP技术发展趋势

16.3创新责任与工程伦理

16.4未来研究方向与学习建议

三、教学周历

注：1.以上一、二、三项内容将作为中文教学大纲，在研究生院中文网页上公布，四、五内容将保存在研究生院。2.开课学期为：春季、秋季或春秋季。3.授课语言为：汉语、英语或双语教学。4.适用学科范围为：公共，一级，二级，三级。5.实践环节为：实验、调研、研究报告等。6.教学方式为：讲课、讨论、实验等。7.学位课程考试必须是笔试。8.课件地址指在网络上已经有的课程课件地址。9.主讲教师简介主要为基本信息（出生年月、性别、学历学位、专业职称等）、研究方向、教学与科研成果，以100至500字为宜。

四、主讲教师简介：

张川： 教授、博士生导师，东南大学青年首席教授，紫金山实验室课题联合负责人，移动信息网络国家科技重大专项首席科学家。东南大学Lab of Efficient Architectures for Digital-communication and Signal-processing (LEADS)负责人。研究方向为面向AI通信算力需求的算法、芯片与工具链，包括：AI基带算法与芯片、基带芯片自动生成EDA系统、2D空时信道编译码、cell-free新型网络架构、强算力网络级AI芯片、通感智算无人系统、射频前端低比特自动量化等。

五、任课教师信息（包括主讲教师）：

六、课程必要性说明

（包括不限于，对比已有课程的重复度？对已有课程的补充性？）

随着人工智能技术在信号处理领域的深度融合，传统DSP算法设计与实现方法正面临智能化转型的迫切需求。本课程《人工智能辅助的数字信号处理算法与实现》旨在填补现有课程体系中AI与DSP交叉领域的教学空白，具有明确的必要性和前瞻性。

与已有课程《面向数字信号处理系统的VLSI设计》相比，本课程不重复其以硬件架构优化和VLSI实现为核心的教学内容，而是聚焦于AI算法在DSP系统中的建模、优化与智能实现，强调算法层面的智能辅助与自动化设计。两门课程形成明显互补：前者注重硬件实现与架构变换，后者注重算法智能优化与系统级AI集成。

本课程的开设将有助于学生：

• 掌握AI辅助DSP算法的前沿理论与方法；

• 培养跨学科融合能力，适应AI+通信/信号处理的研究与工程需求；

• 提升在智能信号处理系统设计与实现方面的创新能力。

此外，本课程紧密结合当前科研与工业界对“AI+通信”“AI+芯片”等方向的人才需求，具有显著的时代性与实用性，是对现有课程体系的重要补充与升级。

七、课程开设审批意见

所在院（系）

审 批 意 见

                 负责人：

                 日  期：

所在学位评定分

委员会审批意见

                      分委员会主席：

                日  期：

研究生院审批意见

                负责人：

                日  期：

  注

说明：1．研究生课程重开、更名申请也采用此表。表格下载：http: /seugs.seu.edu.cn/down/1.asp

2．此表一式三份，交研究生院、院（系）和自留各一份，同时提交电子文档交研究生院。

Application Form For Opening Graduate Courses

School (Department/Institute)：

Course Type: New Open☑   Reopen □   Rename □（Please tick in □, the same below）

1. Course Introduction (including teaching goals and requirements) within 300 words:

This course is designed for graduate students in Information and Communication Engineering, systematically introducing the application of artificial intelligence (AI) technologies in the design and implementation of digital signal processing (DSP) algorithms. It covers intelligent optimization methods such as neural networks and genetic algorithms in modeling, optimization, and hardware implementation of DSP systems. Teaching objectives include: mastering the theoretical foundations of AI-assisted DSP algorithms; developing the ability to use intelligent algorithms to solve practical signal processing problems; and fostering interdisciplinary innovative design thinking. Students are required to have a foundation in digital signal processing, programming, and mathematics. Through a combination of theoretical instruction and project practice, students will complete algorithm simulation and hardware implementation tasks to enhance their engineering research and system implementation capabilities.

2. Teaching Syllabus (including the content of chapters and sections. A sheet can be attached):

Chapter 1: Introduction (2 hours)

1.1 Overview of AI-Empowered New-Generation DSP and VLSI Design

1.2 Development Trends and Typical Applications of AI-DSP Integration

1.3 System Architecture and Intelligent Signal Processing Systems

1.4 Current Development and Challenges in AI-DSP Chips in China

Chapter 2: Core Fundamentals and AI Tool Preparation (2 hours)

2.1 Review of Digital Signal Processing Fundamentals

2.2 Basic Concepts and Algorithm Classification of AI

2.3 Application of MATLAB/Python Toolchain in DSP

2.4 Setup of Intelligent Algorithm Development Environment and Programming Basics

Chapter 3: Review of Baseband Signal Processing Algorithms (2 hours)

3.1 Core Concepts of Traditional DSP Algorithms

3.2 Signal Detection and Channel Equalization Basics

3.3 Coding/Decoding Techniques and Signal Recovery Methods

3.4 Limitations of Traditional Methods and the Need for Intelligence

Chapter 4: AI-Assisted Communication I: Intelligent Signal Detection and Equalization (2 hours)

4.1 Neural Network-Based Signal Detection Algorithms

4.2 Intelligent Channel Equalization Techniques

4.3 Algorithm Simulation and Performance Analysis

4.4 Case Study and Implementation

Chapter 5: AI-Assisted Communication II: Intelligent Channel Coding/Decoding (2 hours)

5.1 Application of Deep Learning in Channel Coding/Decoding

5.2 Design and Optimization of Intelligent Encoders/Decoders

5.3 Simulation Verification and Performance Evaluation

5.4 Comparative Analysis with Traditional Methods

Chapter 6: AI-Assisted Design and Optimization I: Intelligent Evolutionary Algorithms (2 hours)

6.1 Fundamentals of Genetic Algorithms

6.2 Application of Evolutionary Strategies in DSP Hardware Optimization

6.3 Multi-Objective Optimization and Automatic Architecture Search

6.4 Case Study: Hardware Resource and Power Consumption Optimization

Chapter 7: AI-Assisted Design and Optimization II: Intelligent Automatic Generation of Hardware Circuits (2 hours)

7.1 Overview of Intelligent Hardware Generation Methods and Tools

7.2 Machine Learning-Based Automated Circuit Design

7.3 Application of Generative Models in VLSI Design

7.4 Implementation Cases and Performance Analysis

Chapter 8: AI-Assisted Design and Optimization III: Automatic Low-Bit Quantization and Compression (2 hours)

8.1 Overview of Low-Bit Quantization Techniques

8.2 Design and Implementation of Intelligent Quantization Algorithms

8.3 Neural Network Compression and Hardware Acceleration

8.4 Applications and Challenges in Real Systems

Chapter 9: Implementation Architecture of AI-DSP Systems I (2 hours)

9.1 Deployment of Intelligent Algorithms on FPGA Platforms

9.2 Accelerator Design and Optimization

9.3 Hardware Resource Management and Scheduling

9.4 Case Study: Real-Time Signal Processing System Implementation

Chapter 10: Implementation Architecture of AI-DSP Systems II (2 hours)

10.1 Design of Intelligent DSP Cores on ASIC Platforms

10.2 Hardware-Software Co-Optimization Methods

10.3 System-Level Integration and Verification

10.4 Trade-offs Between Low Power and High Performance

Chapter 11: AI-Assisted Design and Optimization IV: Automatic Evaluation and Performance Prediction (2 hours)

11.1 Performance Modeling and Prediction Methods

11.2 Application of Intelligent Algorithms in System Evaluation

11.3 Automated Testing and Verification Processes

11.4 Case Study: End-to-End System Performance Optimization

Chapter 12: In-Depth Case Study: End-to-End AI Communication Baseband Design (2 hours)

12.1 Intelligent Polar Code Encoding/Decoding System

12.2 Intelligent Channel Estimation and Adaptive Modulation

12.3 System Integration and Co-Optimization

12.4 Simulation and Hardware Verification

Chapter 13: System-Level Co-Optimization and Verification (2 hours)

13.1 Multi-Objective System Optimization Methods

13.2 Verification Strategies and Test Platform Construction

13.3 Challenges and Solutions in Practical Engineering

13.4 Case Analysis and Summary

Chapter 14: Frontier Topics I: Automatic Search for Optimal DSP Hardware Architecture (2 hours)

14.1 Automatic Hardware Architecture Search Techniques

14.2 Application of Reinforcement Learning in Architecture Optimization

14.3 Multi-Modal Optimization and Dynamic Reconfiguration

14.4 Development Trends and Research Prospects

Chapter 15: Frontier Topics II: Intelligent Construction Algorithms for Polar Codes (2 hours)

15.1 Review of Polar Code Fundamentals

15.2 Intelligent Construction and Optimization Algorithms

15.3 Applications in 5G/6G Systems

15.4 Performance Analysis and Future Directions

Chapter 16: Course Summary and Outlook (2 hours)

16.1 Review of Course Content and Knowledge Structure

16.2 Development Trends in AI-DSP Technology

16.3 Innovation Responsibility and Engineering Ethics

16.4 Future Research Directions and Learning Suggestions

3. Teaching Schedule:

Note: 1.Above one, two, and three items are used as teaching Syllabus in Chinese and announced on the Chinese website of Graduate School. The four and five items are preserved in Graduate School.

2. Course terms: Spring, Autumn , and Spring-Autumn term.

3. The teaching languages for courses: Chinese, English or Chinese-English.

4. Applicable range of discipline: public, first-class discipline, second-class discipline, and third-class discipline.

5. Practice includes: experiment, investigation, research report, etc.

6. Teaching methods: lecture, seminar, practice, etc.

7. Examination for degree courses must be in paper.

8. Teaching material websites are those which have already been announced.

9. Brief introduction of chief lecturer should include: personal information (date of birth, gender, degree achieved, professional title), research direction, teaching and research achievements. (within 100-500 words)

4. Brief Introduction of Chief lecturer:

Chuan Zhang: Professor and Ph.D. supervisor at the School of Information Science and Engineering, Southeast University; Young Chief Professor of Southeast University; Co-PI at Purple Mountain Laboratories; Chief Scientist of National Major Science and Technology Projects on Mobile Information Networks. He leads the Lab of Efficient Architectures for Digital-communication and Signal-processing (LEADS) at Southeast University. His research focuses on algorithms, chips, and toolchains for AI-driven communication computing, including AI baseband algorithms and chips, automated baseband chip generation EDA systems, 2D spatiotemporal channel coding/decoding, cell-free network architectures, high-computing-power network-level AI chips, integrated communication-sensing-intelligent unmanned systems, and automated low-bit quantization for RF front-ends.

5. Lecturer Information (include chief lecturer)