← Glossary
ML Fundamentals
Classical ML algorithms, learning theory, evaluation methods
17 terms
Agentic workflows
에이전트 워크플로우
Agentic workflows are dynamic workflows in which multiple specialized AI agents collaborate to plan, reason, use tools, …
CoT
사고 과정
CoT, or Chain-of-Thought, is a reasoning technique that prompts or trains large language models to produce or emulate in…
F1 Score
F1 점수
F1 Score is a metric for evaluating classification models. It combines precision (how many predicted positives were actu…
Fine-tuning
파인튜닝
Fine-tuning is the process of continuing training from a pretrained model to adapt it to a specific task, domain, style,…
GPU
그래픽 처리 장치
A GPU is an accelerator that executes uniform, matrix-heavy computations at high throughput via massive parallel threads…
LLM
대규모 언어 모델
A large language model is a deep learning system trained on vast text corpora to understand and generate natural languag…
LoRA
로라
LoRA is a parameter-efficient fine-tuning method that freezes the base model and trains small low-rank adapters instead.
MARL
다중 에이전트 강화학습
Multi-Agent Reinforcement Learning (MARL) is an AI technique where multiple agents learn by interacting with each other …
multi-stage training
다단계 학습
Multi-stage training is a method for developing AI models—especially large language models (LLMs)—by progressively impro…
NLP
자연어 처리
Natural Language Processing (NLP) is an AI discipline that enables computers to interpret and produce human language by …
overfitting
오버피팅
Overfitting is a generalization failure where a model fits training-data noise as if it were signal, seen when training …
post-training
후훈련
Post-training is the stage that adapts a pretrained model to instructions, safety requirements, domain behavior, and hum…
pre-training
사전 훈련
Pre-training is the upstream phase that optimizes a model on large, broad data with self-supervised objectives such as n…
RL
강화 학습
Reinforcement Learning is a machine learning paradigm in which an agent improves its decision policy by interacting with…
Self-Attention
셀프 어텐션
Self-attention is a mechanism where each element in an input sequence compares itself with all other elements to compute…
supervised fine-tuning
지도 미세 조정
Supervised fine-tuning is the process of further training a pre-trained AI model using additional labeled data, where hu…
Synthetic Data
합성 데이터
Synthetic data is artificially generated data created from rules, simulations, statistical models, or generative models …