A-Z of Machine Learning and Computer Vision Terms
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
PyTorch
PyTorch
Q
Q
Quantum Machine Learning
Quantum Machine Learning
Query Strategy (Active Learning)
Query Strategy (Active Learning)
Query Synthesis Methods
Query Synthesis Methods
R
R
RAG Architecture
RAG Architecture
ROC (Receiver Operating Characteristic) Curve
ROC (Receiver Operating Characteristic) Curve
Random Forest
Random Forest
Recall (Sensitivity or True Positive Rate)
Recall (Sensitivity or True Positive Rate)
Recurrent Neural Network (RNN)
Recurrent Neural Network (RNN)
Region-Based CNN (R-CNN)
Region-Based CNN (R-CNN)
Regression (Regression Analysis)
Regression (Regression Analysis)
Regularization Algorithms
Regularization Algorithms
Reinforcement Learning
Reinforcement Learning
Responsible AI
Responsible AI
S
S
Scale Imbalance
Scale Imbalance
Scikit-Learn
Scikit-Learn
Segment Anything Model (SAM)
Segment Anything Model (SAM)
Selective Sampling
Selective Sampling
Self-Supervised Learning
Self-Supervised Learning
Semantic Segmentation
Semantic Segmentation
Semi-supervised Learning
Semi-supervised Learning
Sensitivity and Specificity of Machine Learning
Sensitivity and Specificity of Machine Learning
Sentiment Analysis
Sentiment Analysis
Sliding Window Attention
Sliding Window Attention
Stream-Based Selective Sampling
Stream-Based Selective Sampling
Supervised Learning
Supervised Learning
Support Vector Machine (SVM)
Support Vector Machine (SVM)
Surrogate Model
Surrogate Model
Synthetic Data
Synthetic Data
T
T
Tabular Data
Tabular Data
Text Generation Inference
Text Generation Inference
Training Data
Training Data
Transfer Learning
Transfer Learning
Transformers (Transformer Networks)
Transformers (Transformer Networks)
Triplet Loss
Triplet Loss
True Positive Rate (TPR)
True Positive Rate (TPR)
Type I Error (False Positive)
Type I Error (False Positive)
Type II Error (False Negative)
Type II Error (False Negative)
U
U
Unsupervised Learning
Unsupervised Learning
V
V
Variance (Model Variance)
Variance (Model Variance)
Variational Autoencoders
Variational Autoencoders
W
W
Weak Supervision
Weak Supervision
Weight Decay (L2 Regularization)
Weight Decay (L2 Regularization)
X
X
XAI (Explainable AI)
XAI (Explainable AI)
XGBoost
XGBoost
Y
Y
YOLO (You Only Look Once)
YOLO (You Only Look Once)
Yolo Object Detection
Yolo Object Detection
Z
Z
Zero-Shot Learning
Zero-Shot Learning
B
Batch Normalization
Batch Normalization (BatchNorm) is a technique that stabilizes and accelerates neural network training by normalizing layer activations. It adjusts activations to have zero mean and unit variance within each mini-batch, followed by learnable scaling and shifting parameters. BatchNorm reduces internal covariate shift, allowing higher learning rates and mitigating issues like vanishing/exploding gradients. It also acts as a form of regularization, often reducing the need for dropout in deep networks.
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