# Declarative Learning-Based Programming as an Interface to AI Systems

## TL;DR

This paper reviews and classifies various high-level programming frameworks that integrate multiple machine learning models and reasoning techniques, aiming to simplify the development of complex AI systems for both application and ML experts.

## Contribution

It provides a comprehensive classification and comparative analysis of existing declarative programming frameworks for AI systems, highlighting current challenges and future research directions.

## Key findings

- Existing frameworks vary in techniques and representations used.
- Many frameworks face challenges in usability and scalability.
- Future directions include improving expressiveness and integration.

## Abstract

Data-driven approaches are becoming more common as problem-solving techniques in many areas of research and industry. In most cases, machine learning models are the key component of these solutions, but a solution involves multiple such models, along with significant levels of reasoning with the models' output and input. Current technologies do not make such techniques easy to use for application experts who are not fluent in machine learning nor for machine learning experts who aim at testing ideas and models on real-world data in the context of the overall AI system. We review key efforts made by various AI communities to provide languages for high-level abstractions over learning and reasoning techniques needed for designing complex AI systems. We classify the existing frameworks based on the type of techniques and the data and knowledge representations they use, provide a comparative study of the way they address the challenges of programming real-world applications, and highlight some shortcomings and future directions.