A-Z of Machine Learning and Computer Vision Terms

  • This is some text inside of a div block.
  • This is some text inside of a div block.
  • This is some text inside of a div block.
  • This is some text inside of a div block.
  • This is some text inside of a div block.
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
P

PyTorch

PyTorch is a popular open-source machine learning framework (originating from Facebook’s AI Research lab) used for building and training deep learning models. It provides flexible tools for constructing neural networks and performing tensor computations with strong support for GPU acceleration​.PyTorch is built on the Torch library and is known for its dynamic computation graph approach – meaning the computational graph is built on-the-fly, which makes debugging and developing complex models more intuitive and Pythonic. Researchers and developers favor PyTorch for its ease of use in prototyping: one can define model layers and forward pass logic using standard Python control flow, and PyTorch handles backpropagation automatically with its autograd engine. The framework includes a rich ecosystem: the torch.nn module for layers and loss functions, torch.optim for optimization algorithms, and utilities for data loading (torch.utils.data). PyTorch has become one of the preferred platforms for deep learning research, allowing fast iteration from idea to implementation​.It’s also used in production; features like the TorchScript JIT compiler and TorchServe facilitate the deployment of models after the research phase​.Overall, PyTorch accelerates the path from research prototyping to production by providing an intuitive yet powerful interface for neural network development​.Examples of tasks built with PyTorch include image classification models, NLP transformers, reinforcement learning agents, and more – virtually any AI project that requires training neural networks can be implemented with PyTorch’s toolkit.

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

Ready to Get Started?

Experience the power of automated data curation with Lightly

Learn More