| 1 shot |
AUC |
Active learning |
| Activity recognition |
Alignment |
Anchor box |
| Anomaly detection |
Attention |
Autoencoder |
| Autoregressive |
BERT |
Backpropagation |
| Bag of words |
Bagging |
Batch normalization |
| Bayesian inference |
Bayesian network |
Bleu |
| Boosting |
Bootstrapping |
Bounding box |
| CER |
CNN |
Causal language model |
| Classification |
Claude |
Clustering |
| Confusion matrix |
Context length |
Context window |
| Continual learning |
Contrastive loss |
Convolutional network |
| Coreference |
Cosine similarity |
Cross attention |
| Cross entropy |
Curriculum learning |
Data augmentation |
| Data labeling |
Decision tree |
Decoder |
| Deep learning |
Density estimation |
Dependency parsing |
| Depth estimation |
Diffusion |
Diffusion model |
| Dimensionality reduction |
Discourse |
Discriminative model |
| Distillation |
Doc2Vec |
Domain adaptation |
| Domain generalization |
Dot product |
Dropout |
| Early stopping |
Embedding |
Embedding space |
| Encoder |
Encoder decoder |
Energy based model |
| Ensemble model |
Entity linking |
Euclidean distance |
| Event detection |
Extreme gradient boosting |
F1 score |
| Face recognition |
Fast rcnn |
FastText |
| Faster rcnn |
Feature engineering |
Feature extraction |
| Feature map |
Feature pyramid |
Feature selection |
| Federated learning |
Feedforward network |
Few shot |
| Fine tuning |
GAN |
GCN |
| GNN |
GPT |
Gemini |
| Generalization |
Generative adversarial network |
Generative model |
| Gesture recognition |
GloVe |
Gradient descent |
| Graph attention network |
Graph neural network |
Grid search |
| Grounding |
Hallucination |
Hidden markov model |
| Hierarchical clustering |
Hinge loss |
Hyperparameter |
| Image captioning |
Image classification |
Image denoising |
| Image generation |
Image inpainting |
Image segmentation |
| Image synthesis |
Inference |
Instance segmentation |
| Instruction tuning |
Intent detection |
K means |
| Kernel trick |
Knowledge base |
Knowledge distillation |
| Knowledge graph |
LLaMA |
LSTM |
| Language model |
Language understanding |
Large language model |
| Latent space |
Lemmatization |
Likelihood |
| Linear regression |
Log likelihood |
Logistic regression |
| Logits |
Lora |
Loss function |
| Low rank adaptation |
MAE |
MSE |
| Machine learning |
Manifold learning |
Markov model |
| Mask |
Masked language model |
Mean average precision |
| Meta learning |
Mixture model |
Mixture of experts |
| Model compression |
Multi head attention |
Multi modal |
| Multi task |
N gram |
N shot |
| NER |
NLP |
Naive bayes |
| Named entity recognition |
Natural language processing |
Nearest neighbor |
| Neural network |
Novelty detection |
Object detection |
| Object tracking |
Objective function |
One hot |
| One shot |
Online learning |
Optical flow |
| Optimization |
Outlier detection |
Overfitting |
| PCA |
PaLM |
Parameter efficient |
| Parsing |
Pattern matching |
Pattern recognition |
| Perplexity |
Pose estimation |
Positional encoding |
| Precision |
Pretraining |
Principal component analysis |
| Probabilistic model |
Probability |
Prompt |
| Prompting |
Pruning |
Quantization |
| Question answering |
RAG |
RCNN |
| RLHF |
RNN |
Random forest |
| Recall |
Recurrent network |
Region proposal |
| Regression |
Regularization |
Reinforcement learning |
| Reinforcement learning from human feedback |
Relu |
Representation learning |
| Residual network |
Resnet |
Retrieval augmented generation |
| Roc curve |
Rouge |
SAM |
| Scaling laws |
Scene understanding |
Self attention |
| Self supervised |
Self training |
Semantic parsing |
| Semantic segmentation |
Semantics |
Semi supervised |
| Semi supervision |
Seq2seq |
Sequence model |
| Siamese network |
Sigmoid |
Signal processing |
| Softmax |
Spatiotemporal |
Spectral clustering |
| Statistical model |
Stemming |
Stochastic gradient descent |
| Stopword |
Student model |
Style transfer |
| Summarization |
Super resolution |
Supervised |
| Support vector machine |
Syntax |
Synthetic data |
| T5 |
TF IDF |
Tanh |
| Teacher model |
Temperature |
Template matching |
| Temporal model |
Text classification |
Text generation |
| Time series |
Token |
Tokenization |
| Tokenizer |
Tracking |
Transfer learning |
| Transferability |
Transformer |
Translation |
| Triplet loss |
Tsne |
Umap |
| Underfitting |
Unet |
Unsupervised |
| VIT |
Variational autoencoder |
Vector space |
| Vectorization |
Vision transformer |
Word2Vec |
| XGBoost |
Yolo |
Zero shot |