← Glossary

ML Fundamentals

Classical ML algorithms, learning theory, evaluation methods

17 terms

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