Glossary

0-9

0-shot learning 1-shot learning 2-stage detector 3D convolution 4D data 5G + AI 6DoF pose estimation 7D representation 8-bit quantization 9-layer network

A

AGI / Artificial General Intelligence Algorithm Artificial Intelligence (AI)Attention Autoencoder

B

Backpropagation Batch Normalization BERT Bias Boosting

C

Chatbot Classifier / Classification Clustering CNN / Convolutional Neural Network Cross-Validation

D

Data Augmentation Deep Learning Deepfake Deterministic Model Discriminative Model

E

Embedding Encoder Ensemble Learning Epoch Explainable AI (XAI)

F

Feature Extraction Fine-tuning Forward Propagation Foundation Model Fusion / Multimodal Fusion

G

GAN / Generative Adversarial Network Generative AI Gradient Descent Graph Neural Network (GNN)Grounding

H

Hallucination Heuristic Hidden Layer Hierarchical Model Hyperparameter

I

Imbalanced Data Instance / Sample Instruction tuning Intelligence Amplification / Augmentation Interpretability

J

JAX Jittering Joint Embedding JSONL / JSON-lines Juxtaposition

K

K-means Clustering K-Shot Learning Kernel Trick KL Divergence (Kullback–Leibler Divergence)Knowledge Distillation

L

Large Language Model (LLM)Latent Variable Learning Rate Loss Function LSTM / Long Short-Term Memory

M

Machine Learning (ML)Meta-learning Model Multi-head Attention Multimodal / Multimodality

N

Neural Network NLP / Natural Language Processing NLU / Natural Language Understanding Normalization Novelty Detection / Anomaly Detection

O

Objective Function One-hot Encoding Online Learning Optimizer Overfitting

P

Parameter Policy / Reinforcement Learning Policy Pooling Pretraining Prompt

Q

Q-learning Quality Estimation Quantization Query Queue / Buffer

R

Regularization Reinforcement Learning (RL)Representation Learning Retrieval Augmented Generation (RAG)RNN / Recurrent Neural Network

S

Sampling Self-Supervised Learning Sequence Modeling Softmax Supervised Learning

T

Tokenizer Training Data Transfer Learning Transformer Tuning / Hyperparameter Tuning

U

U-Net Uncertainty Estimation Underfitting Universal Approximation Theorem Unsupervised Learning

V

Validation Set Vanishing / Exploding Gradient Variational Autoencoder (VAE)Vector Embedding Vision Transformer (ViT)

W

Weak Supervision Weight Decay Whitening / Whitening Transformation Word Embedding Workflow

X

X-axis / feature axis XAI / Explainable AI XLM XLNet XOR problem

Y

Y-axis / feature axis Y-transform / YUV YAGNI (You Aren't Gonna Need It)Yield (model yield / throughput)Yoga of AI

Z

Z-score Normalization Zero-centric / Zero-bias initialization Zero-gradient phenomenon Zero-shot Learning / Zero-shot inference Zygosity in augmentation

What is Z-score Normalization

Z-score Normalization, also known as standardization, is a data preprocessing technique commonly used in statistical analysis and machine learning. Its primary purpose is to convert data into a standard normal distribution with a mean of 0 and a standard deviation of 1, thereby eliminating the influence of different scales and units on model training.

In many data analysis tasks, the units and ranges of features may vary, leading to certain features dominating the model training process. Z-score Normalization addresses this by adjusting each data point relative to the mean and standard deviation, making feature distributions more consistent for subsequent analysis and modeling.

The Z-score is calculated using the formula: Z = (X - μ) / σ, where X is the original value, μ is the mean, and σ is the standard deviation. This formula transforms data into a standardized scale.

Z-score Normalization is widely used in various fields, particularly in machine learning models such as Support Vector Machines (SVM), logistic regression, and neural networks. Consistent feature scaling can enhance model convergence speed and accuracy.

Advantages include eliminating dimensional influence between features and aiding in faster algorithm convergence, especially for gradient-based methods. However, it is sensitive to outliers, which can distort the results and is best suited for normally distributed data.

As data science evolves, Z-score Normalization and its variants will continue to find applications in big data processing, deep learning, and real-time data analytics. Researchers are also exploring more robust normalization methods to tackle the challenges posed by modern datasets.

When applying Z-score Normalization, it is crucial to assess the distribution of the data to ensure normality. Additionally, handling outliers should be part of the preprocessing steps to minimize their impact on normalization results.

What is Z-score Normalization - Glossary