A-Z of Machine Learning and Computer Vision Terms
PyTorch
Q
Quantum Machine Learning
Query Strategy (Active Learning)
Query Synthesis Methods
R
RAG Architecture
ROC (Receiver Operating Characteristic) Curve
Random Forest
Recall (Sensitivity or True Positive Rate)
Recurrent Neural Network (RNN)
Region-Based CNN (R-CNN)
Regression (Regression Analysis)
Regularization Algorithms
Reinforcement Learning
Responsible AI
S
Scale Imbalance
Scikit-Learn
Segment Anything Model (SAM)
Selective Sampling
Self-Supervised Learning
Semantic Segmentation
Semi-supervised Learning
Sensitivity and Specificity of Machine Learning
Sentiment Analysis
Sliding Window Attention
Stream-Based Selective Sampling
Supervised Learning
Support Vector Machine (SVM)
Surrogate Model
Synthetic Data
T
Tabular Data
Text Generation Inference
Training Data
Transfer Learning
Transformers (Transformer Networks)
Triplet Loss
True Positive Rate (TPR)
Type I Error (False Positive)
Type II Error (False Negative)
U
Unsupervised Learning
V
Variance (Model Variance)
Variational Autoencoders
W
Weak Supervision
Weight Decay (L2 Regularization)
X
XAI (Explainable AI)
XGBoost
Y
YOLO (You Only Look Once)
Yolo Object Detection
Z
Zero-Shot Learning
Generative Adversarial Networks
GANs are a class of generative models consisting of two neural networks—a generator and a discriminator—that are trained simultaneously in a minimax game. The generator tries to produce data that resembles the real distribution (e.g., realistic images), while the discriminator learns to distinguish between real and generated samples.
The generator improves by learning to fool the discriminator, and the discriminator improves by getting better at spotting fakes. Over time, the generator ideally produces high-quality, realistic outputs.
GANs have been used for image synthesis, super-resolution, style transfer, data augmentation, and even audio and video generation. Variants like DCGAN, StyleGAN, and CycleGAN improve stability or adapt to different tasks (e.g., unpaired image translation).
Training GANs is challenging due to issues like mode collapse (generator produces limited variety), vanishing gradients, and instability. Techniques like feature matching, Wasserstein loss, and spectral normalization help mitigate these problems.
Explore Our Products
Lightly One
Data Selection & Data Viewer
Get data insights and find the perfect selection strategy
Learn More
Lightly Train
Self-Supervised Pretraining
Leverage self-supervised learning to pretrain models
Learn More
Lightly Edge
Smart Data Capturing on Device
Find only the most valuable data directly on devide
Learn More