AI 71
- Double Descent
- 편광 (Polarization)
- DiT (Diffusion Transformer)
- TPE (Tree-structured Parzen Estimator)
- 베이지안 최적화 (Bayesian Optimization)
- Grid Search / Random Search
- LDM (Latent Diffusion Model)
- Optuna: A Next-generation Hyperparameter Optimization Framework
- ReAct: Synergizing Reasoning and Acting in Language Models
- AgentHPO: Large Language Model Agent for Hyper-Parameter Optimization
- FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction
- NeRF (Neural Radiance Fields)
- PSNR / SSIM / LPIPS
- IS / FID / CLIP Score
- Flash Attention
- Muon Optimizer
- Epipolar Geometry
- 사원수 회전 (Quaternion Rotation)
- 2D ↔ 3D 좌표계 변환
- 카메라 캘리브레이션 (Camera Calibration)
- Score SDE와 PF-ODE
- 3D 데이터 표현 방식
- 디퓨전 모델에서의 Guidance
- PEFT (Parameter-Efficient Fine-Tuning)
- 지식 증류 기법 (Knowledge Distillation)
- Score Matching
- DDIM (Denoising Diffusion Implicit Models)
- DDPM (Denoising Diffusion Probabilistic Models)
- 디퓨전 모델의 직관적 이해
- GAN (Generative Adversarial Network)
- VQ-VAE와 VQ-GAN
- VAE (Variational Auto Encoder)
- KV Cahce
- IoU (Intersection over Union)
- AUROC와 AP
- 혼동행렬 (Confusion Matrix)
- VGGNet & ResNet
- Swin Transformer (Shifted Window Transformer)
- 전이 학습 (Transfer Learning)
- 가중치 초기화와 데이터 증강
- CNN에서의 데이터 정규화
- Convolution 연산 종류
- 합성곱 신경망 (Convolutional Neural Network)
- 위치 인코딩 (Positional Encoding)
- 학습
- Normalization
- 비전 트랜스포머 (Vision Transformer)
- Regularization
- 트랜스포머 (Transformer)
- 손실 함수 (Loss Function)
- 옵티마이저 (Optimizer)
- 계산 그래프 (Computational Graphs)
- 경사 하강법 (Gradient Descent)
- 딥러닝 모델의 학습
- MLP (Multi-Layer Perceptron)
- 주성분 분석 (PCA)
- Boosting
- Bagging
- Bias-Variance Decomposition
- Decision Tree
- 커널 트릭 (Kernel Trick)
- SVM (Support Vector Machine)
- 로지스틱 회귀 (Logistic Regression)
- 선형 회귀 (Linear Regression)
- 데이터 행렬과 모델
- Adding Conditional Control to Text-to-Image Diffusion Models
- Null-text Inversion for Editing Real Images using Guided Diffusion Models
- Prompt-to-Prompt Image Editing with Cross Attention Control
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- CLIP: Learning Transferable Visual Models From Natural Language Supervision
- Classifier-Free Diffusion Guidance