IT Wiki

Reset gate

Bidirectional GRU

Transformer architecture

Value

Positional encoding

Encoder

Decoder

Feed-forward network

Attention mechanism

Self-attention

Cross-attention

Multi-head attention

Causal mask

Semantic similarity

Sentence embedding

Contextual embedding

Cosine similarity

Contrastive learning

Retrieval

Magnitude

Euclidean distance

Sparse vector

Dense vector

Tensor

Byte Pair Encoding

Unigram model

Padding

Machine-learning inference

Forward pass

Model serving

Online inference

Prediction

Machine-learning training

Loss function

Backpropagation

Optimizer

Learning rate

Regularization

Distributed training

Pretrained model

Transfer learning

Full fine-tuning

Parameter-efficient fine-tuning

Catastrophic forgetting

Prompt engineering

Context

Few-shot learning

System prompt