Key Terms
Important terminology and concepts used in Tracebloc.
Platform Terms
- data owner
- data scientist
Use Case
A specific AI project or evaluation scenario where data owners and data scientists collaborate.
Client
The Tracebloc component deployed on the data owner's infrastructure that manages data and model execution.
Model
An AI/ML model submitted by data scientists for evaluation on the data owner's infrastructure.
Technical Terms
Federated Learning
A machine learning approach where models are trained across multiple devices while keeping data local.
Differential Privacy
A system for publicly sharing information about a dataset while withholding information about individuals.
Model Weights
The parameters of a trained model that determine its behavior and performance.
Process Terms
Training
The process of teaching a model to make predictions based on data.
Evaluation
The process of assessing a model's performance using predefined metrics.
Fine-tuning
The process of adjusting a pre-trained model for a specific task.