GAN (Generative Adversarial Network)
模型定義
由 generator 與 discriminator 兩個網路組成的架構。Generator 產生合成資料，discriminator 判斷真偽，兩者對抗訓練讓輸出更逼真；影像領域後來多被 diffusion model 取代。
全部術語
AgentAttention MechanismChain-of-ThoughtContext WindowDiffusion ModelDistillationDPO (Direct Preference Optimization)EmbeddingFew-shot PromptingFine-tuningFunction CallingGAN (Generative Adversarial Network)GRPO (Group Relative Policy Optimization)HallucinationInferenceLLM (Large Language Model)LoRA (Low-Rank Adaptation)MCP (Model Context Protocol)MultimodalPrompt EngineeringQLoRA (Quantized LoRA)QuantizationRAG (Retrieval-Augmented Generation)RLHF (Reinforcement Learning from Human Feedback)TemperatureTokenizerTool UseTop-p (Nucleus Sampling)TransformerVector DatabaseZero-shot Prompting