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 1-shot learning

1-shot learning is a machine learning approach that focuses on how to learn from only one training sample for effective classification. This method is particularly useful in scenarios where data is scarce, such as in image recognition and natural language processing. Unlike traditional deep learning models that require large datasets for training, 1-shot learning utilizes prior knowledge and transfer learning to enable models to learn and make accurate predictions from limited samples.

The significance of 1-shot learning lies in its ability to drastically reduce the costs of data collection and annotation, especially in fields like medical imaging and security surveillance where obtaining large amounts of labeled data can be challenging and expensive. By adopting this learning approach, models can quickly adapt to new tasks, minimizing training time and resource consumption.

This learning technique typically involves generating feature embeddings and using distance metrics (such as Euclidean distance or cosine similarity) to determine the similarity between new samples and known samples. Common techniques include Siamese networks, prototype networks, and metric learning.

Typical applications include face recognition, object detection, and voice recognition. For instance, in face recognition, the system only needs to provide a single image of a new face to accurately identify that person. In the future, the trend of 1-shot learning will be towards achieving higher accuracy and broader application areas, especially in real-time processing and online learning.

However, 1-shot learning has its limitations; models can be very sensitive to the choice of samples, and if the quality of samples is poor, the learning outcome may be suboptimal. Therefore, careful selection of samples and consideration of data diversity are essential when applying this method.