Category:Chinese
Jump to navigation
Jump to search
Chinese
Pages in category "Chinese"
The following 200 pages are in this category, out of 346 total.
(previous page) (next page)A
B
- Bayes criterion — 贝叶斯准则
- Bayes minimax criterion — 贝叶斯最小最大准则
- BBQ (Bias Benchmark for Question Answering) — 问答偏见基准
- BERT (language model) — 来自变换器的双向编码器表示
- BERTScore (metric) — BERT评分
- BIG-bench (benchmark) — 大规模基准测试
- Black box — 黑箱
- BLEU (Bilingual Evaluation Understudy) — 双语评估替补
- BLOOM (language model) — 大型开放多语言语言模型
- BOLD (Bias in Open-Ended Language Generation Dataset) — 开放式语言生成偏见数据集
- Branch and bound — 分支定界法
C
- Chain-of-Thought Prompting — 思维链提示
- Chain-of-Verification — 验证链
- Chinchilla (language model) — 龙猫
- Choice (decision-making) — 选择
- Classical methodologies of systems analysis — 系统分析的经典方法
- Classification of system modeling methods — 系统建模方法的分类
- Classification of systems — 系统分类
- Claude (Anthropic) — Claude(Anthropic 的大语言模型)
- Closed system (systems theory) — 封闭系统
- Cognitive bias — 认知偏差
- Cohere Inc. — 科希尔
- Collective choice — 集体选择
- Comparison of alternatives — 方案比较
- Concept of a system — 系统的概念
- Concept 概念
- Conceptual foundations of systems — 系统的概念基础
- Connections in systems — 系统中的连接
- Constitutional AI — 宪法AI
- Constraints — 约束
- Context Window — 上下文窗口
- Contextual forgetting — 上下文遗忘
- Core concepts of systems analysis — 系统分析的基本概念
- Core concepts of systems approach — 系统方法的基本概念
- Core prompt engineering techniques — Prompt Engineering 的主要技术
- Cost–benefit analysis (CBA) — 成本效益分析
- Criterion — 准则 (Criterion)
- Critical path method (CPM) — 关键路径法 (CPM)
- Critical Path — 关键路径
D
- Data Distortion and Bias — 数据失真与偏见
- DBRX (language model) — DBRX(语言模型)
- Decision criteria — 决策准则
- Decision problem — 决策问题
- Decision theory — 决策理论
- Decision theory: Literature — 决策理论相关文献
- Decision theory: Section catalog — 决策理论。章节目录
- Decision theory: Semantic network — 决策理论. 语义网络
- Decision tree — 决策树
- Decision-making matrix model — 矩阵决策模型
- Decision-making problem — 决策问题 (ZH)
- Decision-making under risk — 风险决策
- Decision-making under uncertainty — 不确定性下的决策
- Decision-making — 决策
- Decoder (Transformer) — 解码器
- Decoder-only models (architecture) — 仅解码器
- Decomposition — 分解
- DeepSeek — 深度求索
- Definitions of a system — 系统的定义
- Delphi method — 德尔菲法
- Direct Preference Optimization (DPO) — 直接偏好优化
- Dynamic programming — 动态规划
- Dynamic properties — 动态属性
E
F
- Falcon (language model family) — 猎鹰模型
- Feasible region — 可行域
- Feedback (systems) — 反馈
- Few-Shot and Zero-Shot Learning — 少样本学习与零样本学习
- Fine-tuning (deep learning) — 微调
- FlashAttention — 闪电注意力
- FlashAttention-2 — 闪电注意力-2
- FlashAttention-3 — 闪电注意力-3
- FLORES-200 — FLORES-200(多语言翻译基准)
- Formalization of system models — 系统模型的形式化
- Function calling (LLM) — 函数调用
- Function — 功能
- Fuzzy logic in decision-making — 决策中的模糊逻辑
G
- Gemini (Google) — 双子座
- Gemma (Google) — Gemma 模型
- Generated Knowledge Prompting — 生成知识提示
- Generation bias (LLM) — 生成中的偏见
- GLUE Benchmark — GLUE基准
- Goal (systems analysis) — 系统分析中的目标
- Goal setting — 目标设定
- Goal — 目标
- Google’s large language models — 谷歌大语言模型
- GPT (OpenAI) — 生成式预训练变换模型
- Graph of Thoughts — 思想图
- GraphRAG — 图谱RAG
- Grok (xAI) — Grok(xAI 的大语言模型)
- GSM8K (Grade School Math 8K) — 小学数学8K
H
- HellaSwag Benchmark — HellaSwag 基准测试
- Hierarchy — 层级
- History of operations research — 运筹学的发展
- History of the systems approach — 系统方法的演进
- Hodges-Lehmann criterion — 霍奇斯-莱曼准则
- Homeostasis — 稳态
- Hugging Face — AI社区与平台
- HumanEval Benchmark — HumanEval 基准测试
- Humanity's Last Exam (benchmark) — 人类的最后考试
- Hurwicz criterion — 赫维茨准则
- Hybrid retrieval — 混合检索
- Hypothetical Document Embeddings (HyDE) — 假设性文档扩展
I
L
- LaMDA (Google) — 对话应用语言模型
- LangChain — LLM开发框架
- Languages for system description — 系统描述语言
- Laplace criterion — 拉普拉斯准则
- Large language model architectures — LLM 架构
- Large language model — 大语言模型
- Large language models: Catalog — 模型目录
- Large language models: Section catalog — 大型语言模型:主题目录
- Least-to-most Prompting — 由简入难提示
- Levels of system representation — 系统表示的层次
- Linear programming — 线性规划
- Literature index — 参考文献
- LLaMA (Meta AI) — 大型语言模型Meta AI
- LLM benchmarks — LLM 评测基准
- LLM cost optimization — 优化LLM使用成本
- LLM error mitigation — 减少 LLM 错误
- LLM evaluation — LLM 评估
- LLM hallucinations — LLM幻觉与错误回答
- LLM quality metrics — LLM 质量指标
- LLM-as-a-Judge — 由LLM担当评判者
- LMArena (Chatbot Arena) — 大模型竞技场
- Low-Rank Adaptation (LoRA) — 低秩自适应
M
- Machine learning and data analysis: Section catalog — 机器学习与数据分析. 板块目录
- Machine learning: Literature — 机器学习文献
- Main Page — 主页
- Management — 管理
- Management: Section Index — 管理. 章节目录
- Management: Semantic network — 管理。语义网络
- MATH Benchmark — MATH 基准测试
- Mathematical model — 数学模型
- Mathematical modeling — 数学建模
- Mathematical modeling: Literature — 数学建模文献
- Mathematical modeling: Section catalog — 数学建模. 章节目录
- Mathematical modeling: Semantic network — 数学建模. 语义网络
- Mathematics: Section catalog — 数学 - 板块目录
- MAUVE (metric) — 生成文本评估指标
- Maximax criterion — 最大最大准则
- Maximin criterion (Wald criterion) — 瓦尔德准则
- Meta Prompting — 元提示
- Metasystem — 元系统
- METEOR (metric) — 术语解析
- Methodology and epistemology: Section catalog — 方法论与认识论. 栏目索引
- Minimax regret criterion (Savage criterion) — 萨维奇准则 (Savage's Criterion)
- Mistral AI — 米斯特拉尔
- Mixtral (Mistral AI) — Mixtral(Mistral AI 的专家混合模型)
- Mixture-of-Experts (MoE) — 专家混合模型
- MM-RAG (Multimodal RAG) — 多模态RAG
- MMLU Benchmark — MMLU 基准测试
- Model — 模型
- Modeling (scientific) — 建模
- Modeling process — 建模过程
- Modeling: Section catalog — 建模(目录)
- MT-Bench (benchmark) — MT-Bench 基准测试
- Multi-Agent Debate — 多智能体辩论
- Multi-agent frameworks — 多智能体框架
- Multi-agent prompting — 多智能体提示
- Multi-criteria decision analysis — 多准则决策分析
- Multi-objective optimization — 多目标优化
- Multimodal CoT Prompting — 多模态思维链提示
- Multimodal large language models — 多模态大语言模型
- Multimodal reasoning — 多模态推理
O
- Objective and subjective in systems analysis — 系统分析中的客观与主观
- Objective function — 目标函数
- Observer in the systems approach — 系统方法中的观察者
- Open system (systems theory) — 开放系统
- Open-weight and closed-weight models — 开放权重与封闭权重模型
- OpenAI's large language models — OpenAI 的大型语言模型
- Operation (operations research) — 作业 (运筹学)
- Operations research methodology — 运筹学方法论
- Operations research models — 运筹学模型
- Operations research problems — 运筹学问题