初始化:从 docx 拆分为独立 Markdown 章节
将《设计人工智能:基础与应用》拆分为 38 个 Markdown 文件, 按 11 个部分(上篇6部分+下篇5部分)+ 3 个附录组织。 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,318 @@
|
||||
附录C:关键术语表
|
||||
|
||||
本附录按章节整理书中涉及的关键中英文术语。
|
||||
|
||||
## A
|
||||
|
||||
-------------------------------------------------------
|
||||
中文 英文 章节
|
||||
------------------ ----------------------------- ------
|
||||
自编码器 Autoencoder, AE 11
|
||||
|
||||
注意力机制 Attention 8
|
||||
|
||||
人类反馈强化学习 RLHF 10
|
||||
|
||||
人工智能 AI, Artificial Intelligence 1
|
||||
|
||||
AI for Science AI4S 1
|
||||
|
||||
AI in Education AIED 1
|
||||
-------------------------------------------------------
|
||||
|
||||
## B
|
||||
|
||||
----------------------------------
|
||||
中文 英文 章节
|
||||
------------ -------------- ------
|
||||
边界框 Bounding Box 6
|
||||
|
||||
生物多样性 Biodiversity 24
|
||||
----------------------------------
|
||||
|
||||
## C
|
||||
|
||||
-------------------------------------------
|
||||
中文 英文 章节
|
||||
-------------- ------------------ ---------
|
||||
卷积神经网络 CNN 5, 6, 7
|
||||
|
||||
卷积核 Kernel/Filter 5
|
||||
|
||||
因果推断 Causal Inference \-
|
||||
|
||||
连通性 Connectivity 25
|
||||
|
||||
交叉熵 Cross Entropy 4
|
||||
-------------------------------------------
|
||||
|
||||
## D
|
||||
|
||||
-----------------------------------------
|
||||
中文 英文 章节
|
||||
-------------- ------------------- ------
|
||||
扩散模型 Diffusion Model 11
|
||||
|
||||
数字孪生 Digital Twin 14
|
||||
|
||||
深度学习 Deep Learning 2
|
||||
|
||||
设计生成式AI Generative Design 20
|
||||
-----------------------------------------
|
||||
|
||||
## E
|
||||
|
||||
------------------------------------------
|
||||
中文 英文 章节
|
||||
-------------- -------------------- ------
|
||||
生态系统服务 Ecosystem Services 24
|
||||
|
||||
具身智能 Embodied AI 14
|
||||
|
||||
编码器 Encoder 9
|
||||
|
||||
解码器 Decoder 9
|
||||
------------------------------------------
|
||||
|
||||
## F
|
||||
|
||||
---------------------------------------------
|
||||
中文 英文 章节
|
||||
---------- --------------------------- ------
|
||||
特征图 Feature Map 5
|
||||
|
||||
前馈网络 FFN, Feed-Forward Network 2, 9
|
||||
|
||||
俯瞰 Foundation Model \-
|
||||
---------------------------------------------
|
||||
|
||||
## G
|
||||
|
||||
---------------------------------------------
|
||||
中文 英文 章节
|
||||
-------------- ------------------ -----------
|
||||
生成对抗网络 GAN 11
|
||||
|
||||
生成式AI AIGC 1, 11, 16
|
||||
|
||||
梯度下降 Gradient Descent 4
|
||||
|
||||
图神经网络 GNN 2
|
||||
---------------------------------------------
|
||||
|
||||
## H
|
||||
|
||||
-----------------------------------
|
||||
中文 英文 章节
|
||||
-------- ------------------- ------
|
||||
HITL Human-in-the-Loop 15
|
||||
|
||||
隐藏层 Hidden Layer 3
|
||||
|
||||
超参数 Hyperparameter \-
|
||||
-----------------------------------
|
||||
|
||||
## I
|
||||
|
||||
-----------------------------------------
|
||||
中文 英文 章节
|
||||
---------- ----------------------- ------
|
||||
交并比 IoU 6
|
||||
|
||||
图像分类 Image Classification 6
|
||||
|
||||
实例分割 Instance Segmentation 7
|
||||
-----------------------------------------
|
||||
|
||||
## K
|
||||
|
||||
---------------------------------
|
||||
中文 英文 章节
|
||||
-------- ----------------- ------
|
||||
键 Key 8
|
||||
|
||||
核函数 Kernel Function \-
|
||||
---------------------------------
|
||||
|
||||
## L
|
||||
|
||||
-----------------------------------------
|
||||
中文 英文 章节
|
||||
------------ --------------------- ------
|
||||
大语言模型 LLM 10
|
||||
|
||||
损失函数 Loss Function 4
|
||||
|
||||
学习率 Learning Rate 4
|
||||
|
||||
LoRA Low-Rank Adaptation 12
|
||||
|
||||
潜在空间 Latent Space 11
|
||||
-----------------------------------------
|
||||
|
||||
## M
|
||||
|
||||
--------------------------------------------
|
||||
中文 英文 章节
|
||||
------------ ------------------------ ------
|
||||
多头注意力 Multi-Head Attention 8
|
||||
|
||||
多层感知机 MLP 3, 4
|
||||
|
||||
多模态 Multimodal 10
|
||||
|
||||
MCP Model Context Protocol 15
|
||||
|
||||
平均精度 mAP 6
|
||||
--------------------------------------------
|
||||
|
||||
## N
|
||||
|
||||
--------------------------------------
|
||||
中文 英文 章节
|
||||
-------------- ---------------- ------
|
||||
归一化 Normalization 9
|
||||
|
||||
神经网络 Neural Network 2
|
||||
|
||||
非极大值抑制 NMS 6
|
||||
--------------------------------------
|
||||
|
||||
## O
|
||||
|
||||
---------------------------------------------
|
||||
中文 英文 章节
|
||||
----------------- -------------------- ------
|
||||
目标检测 Object Detection 6
|
||||
|
||||
优化器 Optimizer 4
|
||||
|
||||
One-Stage检测器 One-Stage Detector 6
|
||||
---------------------------------------------
|
||||
|
||||
## P
|
||||
|
||||
---------------------------------------
|
||||
中文 英文 章节
|
||||
---------- --------------------- ------
|
||||
位置编码 Positional Encoding 8
|
||||
|
||||
池化 Pooling 5
|
||||
|
||||
提示工程 Prompt Engineering 10
|
||||
|
||||
预训练 Pre-training 10
|
||||
|
||||
像素 Pixel 7
|
||||
---------------------------------------
|
||||
|
||||
## Q
|
||||
|
||||
---------------------------
|
||||
中文 英文 章节
|
||||
------- ------------ ------
|
||||
查询 Query 8
|
||||
|
||||
Q学习 Q-Learning 14
|
||||
---------------------------
|
||||
|
||||
## R
|
||||
|
||||
------------------------------------------------------
|
||||
中文 英文 章节
|
||||
-------------- -------------------------------- ------
|
||||
RAG Retrieval-Augmented Generation 10
|
||||
|
||||
ReAct Reasoning + Acting 13
|
||||
|
||||
强化学习 RL, Reinforcement Learning 14
|
||||
|
||||
循环神经网络 RNN 2
|
||||
|
||||
残差连接 Residual Connection 9
|
||||
|
||||
值 Value 8
|
||||
|
||||
感受野 Receptive Field 5
|
||||
------------------------------------------------------
|
||||
|
||||
## S
|
||||
|
||||
-----------------------------------------------
|
||||
中文 英文 章节
|
||||
---------------- ----------------------- ------
|
||||
Self-Attention 自注意力 8
|
||||
|
||||
语义分割 Semantic Segmentation 7
|
||||
|
||||
Scaling Law 缩放定律 2
|
||||
|
||||
Sigmoid 激活函数 4
|
||||
|
||||
Softmax 激活函数 4
|
||||
|
||||
境况 State 14
|
||||
|
||||
潜变量 Latent Variable 11
|
||||
|
||||
支持向量机 SVM \-
|
||||
-----------------------------------------------
|
||||
|
||||
## T
|
||||
|
||||
--------------------------------------------
|
||||
中文 英文 章节
|
||||
------------- ----------------------- ------
|
||||
Transformer Transformer架构 9
|
||||
|
||||
拓扑优化 Topology Optimization 21
|
||||
|
||||
Token 令牌/词元 9
|
||||
|
||||
目标检测 Two-Stage Detector 6
|
||||
--------------------------------------------
|
||||
|
||||
## U
|
||||
|
||||
-------------------------------------------------------
|
||||
中文 英文 章节
|
||||
-------------- --------------------------------- ------
|
||||
万能逼近定理 Universal Approximation Theorem 2
|
||||
|
||||
U-Net 分割网络架构 7
|
||||
-------------------------------------------------------
|
||||
|
||||
## V
|
||||
|
||||
--------------------------------------------------
|
||||
中文 英文 章节
|
||||
----------------- ------------------------- ------
|
||||
VAE Variational Autoencoder 11
|
||||
|
||||
向量数据库 Vector Database 10
|
||||
|
||||
视觉Transformer Vision Transformer 5
|
||||
--------------------------------------------------
|
||||
|
||||
## W
|
||||
|
||||
----------------------------------
|
||||
中文 英文 章节
|
||||
---------- ---------------- ------
|
||||
权重 Weight 3
|
||||
|
||||
权重共享 Weight Sharing 5
|
||||
|
||||
权重衰减 Weight Decay \-
|
||||
----------------------------------
|
||||
|
||||
## Y
|
||||
|
||||
-----------------------------------
|
||||
中文 英文 章节
|
||||
------- -------------------- ------
|
||||
YOLO You Only Look Once 6
|
||||
|
||||
-----------------------------------
|
||||
|
||||
**更新日期**:2026年4月
|
||||
@@ -0,0 +1,127 @@
|
||||
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
|
||||
|
||||
4. Universal Approximation Theorem (1989)
|
||||
|
||||
Scaling Laws for Neural Language Models (2020)
|
||||
|
||||
# 计算机视觉
|
||||
|
||||
6. 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
|
||||
|
||||
10. 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
|
||||
|
||||
14. Denoising Diffusion Probabilistic Models (2020)
|
||||
|
||||
High-Resolution Image Synthesis with Latent Diffusion Models (2022)
|
||||
|
||||
ControlNet (2023)
|
||||
|
||||
# AI Agent
|
||||
|
||||
1. LLM Powered Autonomous Agents (2023)
|
||||
|
||||
2. ReAct: Synergizing Reasoning and Acting in Language Models (2022)
|
||||
|
||||
3.
|
||||
|
||||
# 书籍
|
||||
|
||||
5. 深度学习
|
||||
|
||||
6. Deep Learning (Ian Goodfellow et al.)
|
||||
|
||||
7. Neural Networks and Deep Learning (Michael Nielsen)
|
||||
|
||||
8. 强化学习
|
||||
|
||||
9. Reinforcement Learning: An Introduction (Sutton & Barto)
|
||||
|
||||
10.
|
||||
|
||||
# 在线资源
|
||||
|
||||
12. 课程
|
||||
|
||||
13. CS231n: Convolutional Neural Networks for Visual Recognition
|
||||
|
||||
14. Fast.ai Practical Deep Learning for Coders
|
||||
|
||||
## 工具文档
|
||||
|
||||
16. PyTorch: https://pytorch.org/docs/
|
||||
|
||||
17. Ultralytics YOLO: https://docs.ultralytics.com/
|
||||
|
||||
18. LangChain: https://python.langchain.com/
|
||||
|
||||
## 博客
|
||||
|
||||
20. Lil'Log (Lilian Weng): https://lilianweng.github.io/
|
||||
|
||||
21. The Illustrated Transformer: https://jalammar.github.io/illustrated-transformer/
|
||||
|
||||
22.
|
||||
|
||||
# 设计AI相关
|
||||
|
||||
## 学术期刊
|
||||
|
||||
25. Landscape and Urban Planning
|
||||
|
||||
26. Environment and Planning B: Urban Analytics and City Science
|
||||
|
||||
27. Automation in Construction
|
||||
|
||||
## 会议
|
||||
|
||||
29. CAAD Futures
|
||||
|
||||
30. ACADIA
|
||||
|
||||
31. eCAADe
|
||||
|
||||
32.
|
||||
|
||||
# 数据集
|
||||
|
||||
## 计算机视觉
|
||||
|
||||
35. ImageNet
|
||||
|
||||
36. COCO (Common Objects in Context)
|
||||
|
||||
37. MNIST
|
||||
|
||||
## 空间数据
|
||||
|
||||
39. OpenStreetMap
|
||||
|
||||
40. 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
|
||||
@@ -0,0 +1,207 @@
|
||||
附录A:编程工具与资源
|
||||
|
||||
本附录整理AI学习和实践所需的编程工具、框架和资源。
|
||||
|
||||
# Python环境配置
|
||||
|
||||
## Anaconda/Miniconda
|
||||
|
||||
-----------------------------------------------------------------------------------------------------------------
|
||||
工具 大小 特点 下载地址
|
||||
------------- ---------------- ---------------- -----------------------------------------------------------------
|
||||
Anaconda \~500MB 预装常用库 [anaconda.com](https://www.anaconda.com/download)
|
||||
|
||||
Miniconda \~50MB 精简安装 [docs.conda.io](https://docs.conda.io/en/latest/miniconda.html)
|
||||
-----------------------------------------------------------------------------------------------------------------
|
||||
|
||||
## 安装步骤
|
||||
|
||||
\# 1. 下载并安装Miniconda\
|
||||
\# 2. 创建虚拟环境\
|
||||
conda create -n ai-env python=3.10\
|
||||
\
|
||||
\# 3. 激活环境\
|
||||
conda activate ai-env\
|
||||
\
|
||||
\# 4. 安装核心库\
|
||||
pip install torch torchvision numpy pandas scipy
|
||||
|
||||
# 深度学习框架
|
||||
|
||||
## PyTorch
|
||||
|
||||
`pip`` install torch ``torchvision`` ``torchaudio`
|
||||
|
||||
**特点**: - 动态计算图 - 研究友好 - 广泛的社区支持
|
||||
|
||||
**资源**: - [官方文档](https://pytorch.org/docs/) - [中文教程](https://pytorch.zhangxiann.com/)
|
||||
|
||||
## TensorFlow
|
||||
|
||||
`pip`` install ``tensorflow`
|
||||
|
||||
**特点**: - 生产部署优化 - Keras高级API - 跨平台支持
|
||||
|
||||
# 计算机视觉工具
|
||||
|
||||
OpenCV
|
||||
|
||||
`pip`` install ``opencv``-python`
|
||||
|
||||
**功能**:图像处理、视频分析
|
||||
|
||||
Ultralytics YOLO
|
||||
|
||||
`pip`` install ``ultralytics`
|
||||
|
||||
**功能**:目标检测、实例分割
|
||||
|
||||
**使用示例**:
|
||||
|
||||
`from`` ``ultralytics`` ``import`` YOLO`\
|
||||
\
|
||||
`model ``=`` YOLO(``'yolov8n.pt'``)`\
|
||||
`results ``=`` model(``'image.jpg'``)`
|
||||
|
||||
# AIGC工具链
|
||||
|
||||
## Stable Diffusion
|
||||
|
||||
**WebUI**:[Automatic1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
|
||||
|
||||
**ComfyUI**:[GitHub](https://github.com/comfyanonymous/ComfyUI)
|
||||
|
||||
**API调用**:
|
||||
|
||||
`from`` diffusers ``import`` ``StableDiffusionPipeline`\
|
||||
\
|
||||
`pipe ``=`` StableDiffusionPipeline.from_pretrained(``"runwayml/stable-diffusion-v1-5"``)`\
|
||||
`image ``=`` ``pipe(``"a photo of an astronaut riding a horse on mars"``).images[``0``]`
|
||||
|
||||
## ControlNet
|
||||
|
||||
`from`` diffusers ``import`` ``StableDiffusionControlNetPipeline`\
|
||||
\
|
||||
`controlnet`` ``=`` ControlNetModel.from_pretrained(``"lllyasviel/sd-controlnet-canny"``)`\
|
||||
`pipe ``=`` StableDiffusionControlNetPipeline.from_``pretrained(``"runwayml/stable-diffusion-v1-5"``, ``controlnet``=``controlnet``)`
|
||||
|
||||
## Midjourney
|
||||
|
||||
**平台**:Discord **文档**:[docs.midjourney.com](https://docs.midjourney.com/)
|
||||
|
||||
# Agent开发框架
|
||||
|
||||
## LangChain
|
||||
|
||||
`pip`` install ``langchain`` ``langchain-openai`
|
||||
|
||||
**功能**:LLM应用开发框架
|
||||
|
||||
**核心组件**: - Models:LLM接口 - Prompts:提示管理 - Chains:链式调用 - Agents:智能体 - Memory:记忆管理
|
||||
|
||||
LangGraph
|
||||
|
||||
`pip`` install ``langgraph`
|
||||
|
||||
**功能**:状态机式Agent开发
|
||||
|
||||
LlamaIndex
|
||||
|
||||
`pip`` install llama-index`
|
||||
|
||||
**功能**:数据索引与检索(RAG)
|
||||
|
||||
# 开发工具
|
||||
|
||||
VSCode
|
||||
|
||||
**AI开发常用插件**: - Python - Pylance - Jupyter - Copilot
|
||||
|
||||
## Cursor
|
||||
|
||||
**特点**:AI原生IDE **网址**:[cursor.com](https://cursor.com/)
|
||||
|
||||
## Jupyter Lab
|
||||
|
||||
`pip`` install ``jupyterlab`\
|
||||
`jupyter`` lab`
|
||||
|
||||
# 在线学习资源
|
||||
|
||||
## 课程
|
||||
|
||||
--------------------------------------------------------------------------------------------------------------------------------------------------
|
||||
名称 平台 链接
|
||||
------------------- ----------------------- ------------------------------------------------------------------------------------------------------
|
||||
CS231n Stanford [cs231n.stanford.edu](http://cs231n.stanford.edu/)
|
||||
|
||||
Fast.ai fast.ai [course.fast.ai](https://course.fast.ai/)
|
||||
|
||||
吴恩达深度学习 Coursera [coursera.org/specializations/deep-learning](https://www.coursera.org/specializations/deep-learning)
|
||||
--------------------------------------------------------------------------------------------------------------------------------------------------
|
||||
|
||||
## 博客与文档
|
||||
|
||||
1. [Lil'Log](https://lilianweng.github.io/) - AI深度文章
|
||||
|
||||
[The Illustrated Transformer](https://jalammar.github.io/illustrated-transformer/)
|
||||
|
||||
[Distill.pub](https://distill.pub/) - 可视化论文
|
||||
|
||||
## 数据集
|
||||
|
||||
-------------------------------------------------------------------------------------------------------
|
||||
数据集 内容 链接
|
||||
-------------------------- ---------------------- -----------------------------------------------------
|
||||
ImageNet 图像分类 [image-net.org](https://www.image-net.org/)
|
||||
|
||||
COCO 目标检测 [cocodataset.org](https://cocodataset.org/)
|
||||
|
||||
OpenStreetMap 地图数据 [openstreetmap.org](https://www.openstreetmap.org/)
|
||||
-------------------------------------------------------------------------------------------------------
|
||||
|
||||
# 模型资源
|
||||
|
||||
## Hugging Face
|
||||
|
||||
**网址**:[huggingface.co](https://huggingface.co/)
|
||||
|
||||
**功能**: - 模型仓库 - 数据集 - Spaces在线演示
|
||||
|
||||
## 常用模型
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
任务 推荐模型 Hugging Face ID
|
||||
------------ --------------------- ------------------------------------------
|
||||
文生图 Stable Diffusion XL stabilityai/stable-diffusion-xl-base-1.0
|
||||
|
||||
目标检测 YOLOv8 Ultralytics
|
||||
|
||||
语义分割 SAM segment-anything
|
||||
|
||||
大语言模型 Llama 3 meta-llama/Meta-Llama-3-8B
|
||||
-----------------------------------------------------------------------------
|
||||
|
||||
# 硬件资源
|
||||
|
||||
## 云平台
|
||||
|
||||
----------------------------------------
|
||||
平台 特点 适合场景
|
||||
------------------ ---------- ----------
|
||||
Google Colab 免费GPU 学习实验
|
||||
|
||||
Kaggle Notebooks 免费GPU 竞赛
|
||||
|
||||
AutoDL 按时计费 中期项目
|
||||
|
||||
阿里云PAI 国内稳定 生产部署
|
||||
----------------------------------------
|
||||
|
||||
## 本地GPU
|
||||
|
||||
推荐配置: - GPU:RTX 3060 (12GB) 或更高 - 内存:16GB+ - 存储:至少100GB SSD
|
||||
|
||||
# 最后更新
|
||||
|
||||
2026年4月
|
||||
Reference in New Issue
Block a user