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 Zero-shot Learning / Zero-shot inference

Zero-shot Learning (ZSL) is a machine learning approach that enables models to make inferences about unseen classes without having been trained on them. This is particularly useful in scenarios where the model needs to handle new categories, such as in image recognition. The essence of ZSL lies in utilizing the characteristics or attributes of known classes to infer those of unknown classes. For example, a model can classify a new object category by understanding its properties, like recognizing a 'bird' by knowing it is an 'animal with wings'.

In practical applications, Zero-shot Learning is widely used in natural language processing, computer vision, and recommendation systems. By leveraging attribute descriptions or semantic embeddings, models can understand and infer the nature of new categories. For instance, in image classification, a model can identify a 'bird' by grasping the concept of 'winged animals', even if it has never encountered a bird image before.

Zero-shot inference refers to the application of zero-shot learning capabilities during the inference process. This ability is crucial in many application scenarios, especially in data-scarce or emerging fields like autonomous driving, robotics, and personalized recommendations.

The advantages of this technology include enhanced generalization and flexibility of models, reducing the dependence on large amounts of labeled data. However, challenges remain, such as accurately defining relationships between categories and handling noisy attributes.

Looking ahead, as artificial intelligence and deep learning technologies evolve, Zero-shot Learning and Zero-shot inference are expected to find broader applications across various fields, driving the autonomous learning capabilities of intelligent systems.