← Glossary

Deep Learning

Neural network architectures, training techniques, vision, audio

28 terms

Deep Learning LLM & Generative AI
Attention
어텐션
Attention is a neural mechanism that computes a weighted aggregation of information by scoring the similarity between a …
Products & Platforms LLM & Generative AI Deep Learning
Claude
클로드
Claude is Anthropic’s family of large language models delivered through a developer platform — exposed via the Messages …
LLM & Generative AI Data Engineering Deep Learning
Cross-Encoder
크로스 인코더
A Cross-Encoder is an interaction-based neural ranker that concatenates the query and document into a single Transformer…
Infra & Hardware Deep Learning
CUDA
CUDA
CUDA is NVIDIA's programming model and runtime platform for running massively parallel computation on NVIDIA GPUs.
Deep Learning
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…
LLM & Generative AI Deep Learning Data Engineering
Embedding
임베딩
An embedding is a learned vector representation that maps discrete objects or high-dimensional inputs into a continuous …
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,…
Products & Platforms LLM & Generative AI Deep Learning
Gemini
제미나이
Gemini is Google’s family of multimodal generative models delivered through the Gemini API and Vertex AI, handling text,…
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…
Deep Learning LLM & Generative AI
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…
Products & Platforms Deep Learning
Hugging Face
허깅페이스
Hugging Face is an AI development platform built around the Hugging Face Hub and open-source libraries such as Transform…
LLM & Generative AI Infra & Hardware Deep Learning
Inference
추론
Inference is the execution phase where a trained model receives new inputs and computes predictions, classifications, or…
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.
Deep Learning LLM & Generative AI
Model Distillation
모델 증류
Model distillation is a training method that teaches a smaller student model to imitate a larger teacher model's output …
LLM & Generative AI Deep Learning
MoE
전문가 혼합
Mixture of Experts (MoE) is a sparse conditional-computation architecture in which a gating/router network selects a sma…
LLM & Generative AI Deep Learning
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…
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 …
Infra & Hardware Deep Learning
Quantization
양자화
Quantization is a neural‑network compression‑and‑acceleration technique that represents weights and activations with low…
Deep Learning LLM & Generative AI
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…
LLM & Generative AI Deep Learning
RLHF
인간 피드백 강화학습
Reinforcement Learning from Human Feedback (RLHF) is a post-training alignment method that treats a language model as a …
CS Fundamentals Deep Learning LLM & Generative AI
RoPE
RoPE(회전 위치 인코딩)
RoPE, or Rotary Position Embedding, is a Transformer positional encoding method that rotates query and key vectors by po…
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…
Deep Learning LLM & Generative AI
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…
Products & Platforms Deep Learning
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…
Deep Learning LLM & Generative AI
Transformer
트랜스포머
A Transformer is a neural network architecture that stacks self-attention and feed-forward blocks to learn relationships…
Deep Learning LLM & Generative AI
vision-language model
비전-언어 모델
A vision-language model is an artificial intelligence model designed to simultaneously understand and process both visua…
Deep Learning LLM & Generative AI
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 …