Common-Description Learning: A Framework for Learning Algorithms and Generating Subproblems from Few Examples
This addresses the challenge of enabling machines to learn from limited data like humans, potentially improving language understanding, though it appears incremental as it builds on existing learning algorithm concepts.
The paper tackles the problem of learning algorithms from few examples by introducing the Common-Description Learning (CDL) framework, which learns complex patterns and breaks them into simpler subproblems, achieving perfect interpretability and tested on 32 multi-task datasets.
Current learning algorithms face many difficulties in learning simple patterns and using them to learn more complex ones. They also require more examples than humans do to learn the same pattern, assuming no prior knowledge. In this paper, a new learning framework is introduced that is called common-description learning (CDL). This framework has been tested on 32 small multi-task datasets, and the results show that it was able to learn complex algorithms from a few number of examples. The final model is perfectly interpretable and its depth depends on the question. What is meant by depth here is that whenever needed, the model learns to break down the problem into simpler subproblems and solves them using previously learned models. Finally, we explain the capabilities of our framework in discovering complex relations in data and how it can help in improving language understanding in machines.