Flashcards
Click cards to flip and reveal definitions. Use keyboard arrows to navigate.
Artificial Intelligence
The simulation of human intelligence in machines programmed to think and learn like humans. Includes ML, NLP, computer vision, and robotics.
Machine Learning
A subset of AI that enables systems to learn and improve from experience without explicit programming. Builds models from sample data.
Deep Learning
A specialized ML technique using neural networks with multiple layers to learn hierarchical data representations. Excels with unstructured data.
PMI-CPMAI
PMI Certified Professional in Managing AI - A certification and methodology for managing AI projects using an 8-phase structured approach.
AI Project Lifecycle
The iterative process of discovering, designing, developing, and deploying AI solutions. Differs from traditional software due to its experimental nature.
Feasibility Assessment
An evaluation of technical, business, and operational viability before committing resources to an AI project.
Data Lineage
The documentation of data's origin, movement, transformations, and storage throughout its lifecycle.
Feature Engineering
The process of creating new input variables from existing data to improve model performance.
Data Augmentation
Applying transformations to existing training data to increase dataset diversity without collecting new data.
Transfer Learning
Using knowledge from a pre-trained model to accelerate learning on a new, related task.
Hyperparameters
Settings that control the model training process (e.g., learning rate, batch size) that must be set before training.
Overfitting
When a model memorizes training data instead of learning generalizable patterns, causing poor performance on new data.
Cross-Validation
A technique to assess model performance by training and validating on different subsets of data.
Model Drift
Decline in model performance over time due to changes in data patterns or the environment.
MLOps
DevOps practices applied to machine learning systems, including CI/CD, monitoring, and automated retraining.
Model Versioning
Tracking and managing different iterations of models, including weights, hyperparameters, and performance metrics.
Bias in AI
Systematic errors in model predictions that unfairly favor certain groups or outcomes over others.
F1 Score
The harmonic mean of precision and recall, providing a balanced measure for classification performance.
ROC-AUC
ROC (Receiver Operating Characteristic) curve area under the curve. Measures classification performance across all thresholds.