2026_DesignAI/officefile/appendix/references.md

参考文献

本部分整理教材中引用的论文、书籍和在线资源。

---

论文

基础理论

• Universal Approximation Theorem (1989)
• Scaling Laws for Neural Language Models (2020)

计算机视觉

• AlexNet (2012) - ImageNet Classification with Deep Convolutional Neural Networks
• ResNet (2015) - Deep Residual Learning for Image Recognition
• YOLO (2016) - You Only Look Once: Unified, Real-Time Object Detection
• U-Net (2015) - Convolutional Networks for Biomedical Image Segmentation

Transformer与大模型

• Attention Is All You Need (2017)
• BERT: Pre-training of Deep Bidirectional Transformers (2018)
• GPT-3: Language Models are Few-Shot Learners (2020)
• Training Language Models to Follow Instructions with Human Feedback (2022)

生成式AI

• Denoising Diffusion Probabilistic Models (2020)
• High-Resolution Image Synthesis with Latent Diffusion Models (2022)
• ControlNet (2023)

AI Agent

• LLM Powered Autonomous Agents (2023)
• ReAct: Synergizing Reasoning and Acting in Language Models (2022)

---

书籍

深度学习

• Deep Learning (Ian Goodfellow et al.)
• Neural Networks and Deep Learning (Michael Nielsen)

强化学习

• Reinforcement Learning: An Introduction (Sutton & Barto)

---

在线资源

课程

• CS231n: Convolutional Neural Networks for Visual Recognition
• Fast.ai Practical Deep Learning for Coders

工具文档

• PyTorch: https://pytorch.org/docs/
• Ultralytics YOLO: https://docs.ultralytics.com/
• LangChain: https://python.langchain.com/

博客

• Lil'Log (Lilian Weng): https://lilianweng.github.io/
• The Illustrated Transformer: https://jalammar.github.io/illustrated-transformer/

---

设计AI相关

学术期刊

• Landscape and Urban Planning
• Environment and Planning B: Urban Analytics and City Science
• Automation in Construction

会议

• CAAD Futures
• ACADIA
• eCAADe

---

数据集

计算机视觉

• ImageNet
• COCO (Common Objects in Context)
• MNIST

空间数据

• OpenStreetMap
• 路网数据、POI数据等

---

许可说明

部分内容引用自公开资源，遵循相应许可协议使用。

---

最后更新：2026年4月