- cnn
- AlexNet
- ReLU
- nlp
- pre-training
- dropout
- RNN
- 머신러닝
- transformer
- attention
- Fine-tuning
- paper review
- 다층 퍼셉트론
- Recurrent Neural Network
- Data augmentation
- Activation function
- cross entropy
- bagging
- loss function
- regularization
- batch normalization
- classification
- LSTM
- 딥러닝
- stationarity
- Luong attention
- attention score
- Correlation Distance
- deconvolutional network
- Local Response Normalization
- residual
- encoder-decoder
- Overlapping Pooling
- 데이터 분석 프로젝트
- Lenet-5
- euclidean distance
- chain rule
- oversampling
- time series
- Image Classification
- Multi-Head Attention
- ZFNet
- 분산 학습
- seq2seq
- Residual Connection
- GoogLeNet
- 합성곱 신경망
- Early stopping
- Active learning
- object detection
- BPTT
- GAN
- AdaGrad
- Maximum likelihood estimation
- feature extraction
- PyTorch
- Random Forest
- Unsupervised Learning
- Cost Function
- pooling
- language model
- sigmoid
- 비지도 학습
- 지도 학습
- 논문 리뷰
- Regression
- Deep Learning
- Feature Map
- ensemble
- GRU
- optimization
- SOFTMAX
- Bert
- entropy
- SSE
- Decoder
- ML
- Mahalanobis distance
- pls
- adam
- VISION
- dice loss
- focal loss for dense object detection
- two-stage detector
- one-stage detector
- position-wise processing
- feed-forward network
- gradient clipping
- meft
- tensor_hook
- full_backward_hook
- forward_pre_hook
- forward_hook
- multi-process
- loss reduction
- ring all-reduce
- gradient bucketing
- distributed data parallel
- gloo
- nccl
- distributed programming
- process group
- collective communication
- Data Parallel
- feature invariance
- feature visualization
- RGB intensity
- multiple GPUs
- NLinear
- DLinear
- look-back window
- permutation-invariant
- temporal relation
- local positional information
- DMS forecasting
- Transformer-Based LTSF Solutions
- LTSF
- Long-term Time Series Forecasting
- online update
- anomaly score
- temporal correlation
- temporal dependency
- collective anomaly
- contextual anomaly
- point anomaly
- invertibility
- moving average model
- autoregressive model
- backshift
- random walk model
- uniform input representation
- dynamic decoding
- generative style decoder
- self-attention distilling operation
- sparse attention
- ProbSparse self-attention
- LSTF
- Long Sequence Time-Series Forecasting
- innovation state space model
- error correction
- state space model
- damped trend
- simple exponential smoothing
- seasonally adjusted
- seasonal indices
- seasonally adjusted data
- multiplicative decomposition
- additive decomposition
- probabilistic forecasts
- point estimates
- Bayesian Filtering
- regression spline
- piecewise regression
- Spurious regression
- coefficient of determination
- residual standard error
- Breusch-Godfrey
- Last Square Estimation
- scatterplot matrix
- KNN-TAPT
- curated-TAPT
- continued pretraining
- human curated-TAPT
- model adaptation
- TAPT
- task-adaptive pretraining
- domain-adaptive pretraining
- noising function
- sentence sguffling
- text inflling
- left-to-right autoregressive decoder
- bidirectional encoder
- denosing autoencoder
- multi-task learning
- WebText
- CC-NEWS
- Dynamic masking
- wordpiece embedding
- next sentence prediction
- deep bidirectional transformer
- masked language model
- Transformer Decoder
- word representation
- bidirectional LSTM
- downstream task
- Embeddings from Language Models
- Position Encoding
- Position-wise Feed-Forward Neural Network
- Residual Dropout
- Scaled Dot-Product Attention
- Trasformer
- Input-Feeding
- global attentional model
- Local attentional model
- Bahdanau Attention
- Neural Machine Translation
- linearly embedding
- trasnfer learning
- patch embedding
- positional embedding
- Light GBM
- Generative Adversarial Nets
- Borderline-SMOTE
- Condensed Nearest Neighbor
- Tomek Links
- Random Undersampling
- Ward Distance
- Class imbalance
- Layer-Normalization
- Input Embedding
- Feed Forward Neural Network
- Masked Self-Attention
- Self-Attetion
- Bahadana attention
- feedforward neural network
- NIPALS
- partial least squres
- PCA Loading
- elbow point
- Lagrangian Primal
- Lagrangian Dual
- Lagrangian multiplier
- Linear SVM
- KKT conditions
- Lagrangian formulation
- backward propagtion through time
- Time Seires Data
- Generalization error
- misclassification rate
- classification tree
- decision tree model
- Weighted KNN
- Spearman Rank Correlation Distance
- distance measure
- K-Nearest-Neighbors
- basicblock
- bottleneck block
- shrinkage
- expected MSE
- explanatory modeling
- predictive modeling
- OOB error
- context vector
- residual connect
- dilated convolution
- infinitely strong prior
- He Initialization
- Nesterov Momentum
- SGD Momentum
- adaptive learning rate
- minibatch
- gradient check
- logit transform
- Gradient Saturation
- Least Squares Estimation
- 범주예측
- 수치예측
- 김성범 교수님
- 핵심 머신러닝
- 머신러닝 모델링
- 검증 데이터
- 학습 데이터
- stochastic descent gradient
- Layer Normalization
- Stable Diffusion Model
- Roboflow.
- 도배 하자 이미지 분류 경진대회
- large language model
- elastic-net
- WM-811k
- least margin
- least confidence
- sampling strategy
- WBM
- 반도체 웨이퍼 이미지
- random subspace
- multi-processing
- 액티브 러닝
- Expected Model Change
- Core-Set
- Learning Loss
- Query-By-Committee
- Uncertainty Sampling
- yolov8
- model parameter
- 소프트 보팅
- 하드 보팅
- 데이터 프로젝트
- Average Pooling
- minimax loss
- Generative Adversarial Networks
- 빅콘테스트
- cross_validate
- 웨이퍼 맵
- EDS공정
- transposed convolution
- F1-score
- Gated Recurrent Unit
- regression tree
- Pointwise convolution
- Max pooling
- Xavier initialization
- vision transformer
- 불량 탐지
- EDS 테스트
- 웨이퍼 맵 데이터
- feature extractor
- activation map
- Ridge regression
- Image Data
- cross entropy error
- sum of squares error
- Softmax Function
- Sigmoid Function
- GPT-2
- Zero-shot learning
- stratified k-fold
- DAPT
- seasonality
- linear layer
- Scatterplot
- representation
- Weighted Moving Average
- Inductive bias
- NAND 게이트
- OR 게이트
- AND 게이트
- RoBERTa
- ffn
- Moving average
- 파이썬 머신러닝 완벽 가이드
- exponential smoothing
- 딥러닝 논문
- 점추정
- 오버샘플링
- PACF
- Stacking
- AutoReload
- Correlation Coefficient
- 계산 그래프
- 단층 퍼셉트론
- discriminator
- Generative Adversarial Network
- 손실 함수
- 수치 미분
- XOR 게이트
- 밑바닥부터 시작하는 딥러닝
- undersampling
- 불균형 데이터
- autocorrelation
- Fully-connected layer
- Learning Rate Decay
- GridSearchCV
- cross_val_score
- Positional Encoding
- Depthwise Convolution
- SMOTE
- Weight Decay
- Attention Mechanism
- Truncated BPTT
- K-fold cross validation
- 선형회귀모델
- Step Function
- Maxout
- leaky ReLU
- Manhattan Distance
- 교차 검증
- 이미지 분류
- Vanilla RNN
- Bottleneck Layer
- ResNet
- VGGNet
- Convolutional Layer
- Gradient Vanishing
- 연쇄법칙
- Embedding
- DACON
- 편미분
- 데이터 전처리
- Principal components analysis
- lasso regression
- Focal loss
- Standardization
- Informer
- catboost
- 과적합
- Overfitting
- cross entropy loss
- multiple linear regression
- Multicollinearity
- 결정계수
- information gain
- initialization
- XGBoost
- affine transformation
- Cross Validation
- r-cnn
- critical point
- Differencing
- Backpropagation
- K-Means Clustering
- Hierarchical Clustering
- self-attention
- transfer learning
- RMSProp
- SGD
- dimension reduction
- MLP
- Network In Network
- 강화 학습
- feature selection
- Language Modeling
- neural network
- Forecasting
- 손실함수
- 역전파
- 순전파
- NMT
- 퍼셉트론
- Correspondence
- 구간추정
- Supervised Learning
- Gradient Descent
- Linear Regression
- stride
- support vector machine
- resampling
- Xavier
- 가중치
- VIT
- imagenet
- linear transformation
- Convolutional Neural Networks
- ACF
- 스태킹
- convolution
- 반도체 웨이퍼
- saddle point
- anomaly detection
- Multi-Thread
- bart
- Bloom filter
- translation
- 잔차
- SVM
- Gini
- eigenvalue
- eigenvector
- Normalization
- message passing
- 머신 러닝
- 매개변수
- Silhouette
- activation
- Epoch
- overshooting
- Momentum
- Hook
- adaboost
- 랜덤 포레스트
- boosting
- 최소제곱법
- DDP
- mse
- Bald
- Generator
- clustering
- GBM
- 데이터 분석
- White Noise
- PCA
- ANOVA
- PLM
- 신경망
- dp
- Vampire
- Elmo
- odds ratio
- logistic regression
- 비용함수
- 이미지 생성
- padding
- Margin
- bootstrap
- MPI
- GPT
- 핀다
- DL
- inception
- 데이터 모델링
- YOLO
- Trend
- MLM
- Encoder
- 파라미터
- cycle
- 분류
- 모델링
- Switch
- 기울기
- Segmentation
- 반도체
- 논문
- blue
- NSP
- Noise
- SSD
- 프로젝트
- 패딩
- ETS
- KNN
- p2p
태그 목록