← Glossary
Deep Learning
Neural network architectures, training techniques, vision, audio
28 terms
Attention
어텐션
Attention is a neural mechanism that computes a weighted aggregation of information by scoring the similarity between a …
Claude
클로드
Claude is Anthropic’s family of large language models delivered through a developer platform — exposed via the Messages …
Cross-Encoder
크로스 인코더
A Cross-Encoder is an interaction-based neural ranker that concatenates the query and document into a single Transformer…
CUDA
CUDA
CUDA is NVIDIA's programming model and runtime platform for running massively parallel computation on NVIDIA GPUs.
diffusion model
확산 모델
A diffusion model is a deep learning-based generative model in AI that creates new data by gradually denoising random no…
Embedding
임베딩
An embedding is a learned vector representation that maps discrete objects or high-dimensional inputs into a continuous …
Fine-tuning
파인튜닝
Fine-tuning is the process of continuing training from a pretrained model to adapt it to a specific task, domain, style,…
Gemini
제미나이
Gemini is Google’s family of multimodal generative models delivered through the Gemini API and Vertex AI, handling text,…
GPU
그래픽 처리 장치
A GPU is an accelerator that executes uniform, matrix-heavy computations at high throughput via massive parallel threads…
grouped-query attention
그룹 쿼리 어텐션
Grouped-query attention is a method used in large language models (LLMs) and transformer-based AI systems to process sev…
Hugging Face
허깅페이스
Hugging Face is an AI development platform built around the Hugging Face Hub and open-source libraries such as Transform…
Inference
추론
Inference is the execution phase where a trained model receives new inputs and computes predictions, classifications, or…
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.
Model Distillation
모델 증류
Model distillation is a training method that teaches a smaller student model to imitate a larger teacher model's output …
MoE
전문가 혼합
Mixture of Experts (MoE) is a sparse conditional-computation architecture in which a gating/router network selects a sma…
Multimodal Model
멀티모달 모델
A multimodal model is an AI model designed to process or generate across two or more data modalities, such as text, imag…
NLP
자연어 처리
Natural Language Processing (NLP) is an AI discipline that enables computers to interpret and produce human language by …
Quantization
양자화
Quantization is a neural‑network compression‑and‑acceleration technique that represents weights and activations with low…
recurrent mechanism
순환 메커니즘
A recurrent mechanism refers to an architectural design in AI models where the output from a previous step is fed back a…
RLHF
인간 피드백 강화학습
Reinforcement Learning from Human Feedback (RLHF) is a post-training alignment method that treats a language model as a …
RoPE
RoPE(회전 위치 인코딩)
RoPE, or Rotary Position Embedding, is a Transformer positional encoding method that rotates query and key vectors by po…
Self-Attention
셀프 어텐션
Self-attention is a mechanism where each element in an input sequence compares itself with all other elements to compute…
Self-Supervised Pretext Tasks
자기지도 사전학습 과제
Self-supervised pretext tasks are label-free training objectives that exploit intrinsic structure in unlabeled data to l…
Sora video model
소라 비디오 모델
The Sora video model is an AI system developed by OpenAI that generates high-quality videos from text prompts. You simpl…
Transformer
트랜스포머
A Transformer is a neural network architecture that stacks self-attention and feed-forward blocks to learn relationships…
vision-language model
비전-언어 모델
A vision-language model is an artificial intelligence model designed to simultaneously understand and process both visua…
Visual Instruction Tuning
시각 지시 학습
Visual instruction tuning is a supervised fine-tuning approach that aligns a vision encoder with a large language model …