MOSAIC, acomparison framework for machine learning models
This framework addresses the problem of cumbersome and error-prone model development for researchers, engineers, and practitioners in machine learning, though it is incremental as it builds on existing tools and practices.
The authors introduced MOSAIC, a Python framework designed to accelerate machine learning studies by simplifying and speeding up the implementation and testing of arbitrary network architectures and datasets, resulting in a tool that reduces errors and provides a full execution pipeline from configuration to performance metrics.
We introduce MOSAIC, a Python program for machine learning models. Our framework is developed with in mind accelerating machine learning studies through making implementing and testing arbitrary network architectures and data sets simpler, faster and less error-prone. MOSAIC features a full execution pipeline, from declaring the models, data and related hyperparameters within a simple configuration file, to the generation of ready-to-interpret figures and performance metrics. It also includes an advanced run management, stores the results within a database, and incorporates several run monitoring options. Through all these functionalities, the framework should provide a useful tool for researchers, engineers, and general practitioners of machine learning.