AI & Machine Learning

Preparation and standardization of raw data through cleaning, transformation, and normalization to improve analyses and models.

Concepts and practices for transforming raw data into informative features to improve predictive models.

Method for centrally storing, versioning and serving ML features for training and inference.

Inference is the application of a trained model to new data to produce predictions or decisions. It focuses on latency, scalability and resource optimization for production use.

Concept and practice for reliably delivering, operating and versioning trained machine learning models in production environments.

Concepts and practices for exposing trained machine learning models to production traffic, focusing on scalability, versioning and observability.

Statistical technique for robustly evaluating and comparing predictive models by repeatedly splitting data into training and test sets.

Systematic assessment of machine learning models using metrics, validation techniques and error analysis to decide on deployment readiness.

Model validation comprises practices and criteria to evaluate machine learning models, ensuring robustness, generalization and fairness. It defines tests, metrics and acceptance criteria across training and production stages.

Learning paradigm using deep neural networks for automatic feature extraction and prediction.

Machine learning extracts patterns and makes predictions from data using statistical models and algorithms.

Reinforcement Learning is a machine learning paradigm where agents learn to select optimal actions in sequential problems via rewards and penalties.

Technique for automated search of optimal hyperparameters for ML models to improve performance and generalization.

Process by which a machine learning model learns parameters from data to enable generalizable predictions.

Structural principles and design patterns for artificial neural networks that define layers, connectivity, and activation functions.

MLOps describes organizational practices and technical processes for production deployment, monitoring, and governance of machine learning models.

Framework for controlling, monitoring and accountability of models, especially ML models. Focuses on compliance, reproducibility and lifecycle control.

Continuous monitoring of machine learning models in production to detect performance degradation, drift, and faulty predictions.