A-Z of Machine Learning and Computer Vision Terms
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
A
A
Activation Function
Activation Function
Active Learning
Active Learning
AI Agent
AI Agent
AI Assistants
AI Assistants
AI Assisted Labeling
AI Assisted Labeling
Algorithm
Algorithm
Anchor Boxes
Anchor Boxes
Anomaly Detection
Anomaly Detection
Artificial Intelligence (AI)
Artificial Intelligence (AI)
Attribute
Attribute
B
B
Backpropagation
Backpropagation
Backpropagation
Backpropagation
Bagging
Bagging
Batch
Batch
Batch Normalization
Batch Normalization
Bayesian Network
Bayesian Network
Bias
Bias
Big Data
Big Data
Binary Classification
Binary Classification
Blur
Blur
Boosting
Boosting
Bounding Box
Bounding Box
C
C
Calibration
Calibration
Calibration Curve
Calibration Curve
Canonical Correlation Analysis (CCA)
Canonical Correlation Analysis (CCA)
Case-Based Reasoning
Case-Based Reasoning
Chain of Thought (CoT)
Chain of Thought (CoT)
ChatGPT
ChatGPT
Chi-Squared Automatic Interaction Detection (CHAID)
Chi-Squared Automatic Interaction Detection (CHAID)
Class Boundary (Statistics & Machine Learning)
Class Boundary (Statistics & Machine Learning)
Class Imbalance
Class Imbalance
Clustering
Clustering
COCO
COCO
Collaborative Filtering
Collaborative Filtering
Computer Vision
Computer Vision
Computer Vision Model
Computer Vision Model
Concept Drift
Concept Drift
Conditional Random Field (CRF)
Conditional Random Field (CRF)
Confusion Matrix
Confusion Matrix
Constrained Clustering
Constrained Clustering
Contrastive Learning
Contrastive Learning
Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
Cross-entropy Loss
Cross-entropy Loss
Cross-Validation
Cross-Validation
D
D
Data Approximation
Data Approximation
Data Augmentation
Data Augmentation
Data Drift
Data Drift
Data Error
Data Error
Data Mining
Data Mining
Data Operations
Data Operations
Data Pre-processing
Data Pre-processing
Data Quality
Data Quality
Dataset
Dataset
Decision Boundary
Decision Boundary
Decision List
Decision List
Decision Stump
Decision Stump
Decision Tree
Decision Tree
Deep Learning
Deep Learning
Deep Neural Networks
Deep Neural Networks
Deep Reinforcement Learning (DRL)
Deep Reinforcement Learning (DRL)
DICOM
DICOM
Dimensionality Reduction
Dimensionality Reduction
Dimensionality Reduction
Dimensionality Reduction
Dropout
Dropout
Dynamic and Event-Based Classifications
Dynamic and Event-Based Classifications
E
E
Edge Cases
Edge Cases
Edge Computing
Edge Computing
Edge Detection
Edge Detection
Elastic Net
Elastic Net
Embedding Spaces
Embedding Spaces
Ensemble Learning
Ensemble Learning
Epoch
Epoch
Expectation-Maximization Algorithm (EM)
Expectation-Maximization Algorithm (EM)
Extreme Learning Machine
Extreme Learning Machine
F
F
F1 Score
F1 Score
Factor Analysis
Factor Analysis
False Positive Rate
False Positive Rate
Feature
Feature
Feature Extraction
Feature Extraction
Feature Hashing
Feature Hashing
Feature Learning
Feature Learning
Feature Scaling
Feature Scaling
Feature Selection
Feature Selection
Feature Vector
Feature Vector
Fisher’s Linear Discriminant
Fisher’s Linear Discriminant
Foundation Models
Foundation Models
FP-Growth Algorithm
FP-Growth Algorithm
Frame Rate
Frame Rate
Frames Per Second (FPS)
Frames Per Second (FPS)
Fully Connected Layer
Fully Connected Layer
Fuzzy Logic
Fuzzy Logic
G
G
Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)
Generative Adversarial Networks
Generative Adversarial Networks
L
Long Short-Term Memory (LSTM)
Long Short-Term Memory (LSTM) networks are a type of Recurrent Neural Network (RNN) specifically designed to learn long-range dependencies in sequential data. They address the vanishing gradient problem that affects standard RNNs, which struggle to retain information over many time steps.
LSTMs introduce a special memory cell that maintains information over time and three types of gates that control the flow of information:
- Forget gate: Decides what information to discard from the cell state.
- Input gate: Determines which new information to store.
- Output gate: Controls what part of the cell state to output.
This gating mechanism allows LSTMs to selectively remember or forget information as needed, making them highly effective in tasks requiring memory of past inputs.
LSTMs are commonly used in:
- Natural language processing (e.g., language modeling, machine translation),
- Speech recognition,
- Time series forecasting,
- Sequential recommendation systems.
Explore Our Products
.svg)
LightlyStudio
Data Curation, Labeling & QA
Get data insights and find the perfect
selection strategy, label &Â QA data.
Learn More
LightlyTrain
Self-Supervised Pretraining &Â Fine-Tuning
Leverage self-supervised learning to pretrain
and fine-tune models
Learn More
