Human-like machine learning: limitations and suggestions
This is an incremental discussion paper that highlights foundational issues in ML training paradigms, relevant for researchers and practitioners seeking more efficient learning methods.
The paper critiques the human-like supervised learning approach in machine learning for its heavy reliance on large, high-quality annotated data, and suggests exploring alternative non-data-driven methods to address limitations with limited data.
This paper attempts to address the issues of machine learning in its current implementation. It is known that machine learning algorithms require a significant amount of data for training purposes, whereas recent developments in deep learning have increased this requirement dramatically. The performance of an algorithm depends on the quality of data and hence, algorithms are as good as the data they are trained on. Supervised learning is developed based on human learning processes by analysing named (i.e. annotated) objects, scenes and actions. Whether training on large quantities of data (i.e. big data) is the right or the wrong approach, is debatable. The fact is, that training algorithms the same way we learn ourselves, comes with limitations. This paper discusses the issues around applying a human-like approach to train algorithms and the implications of this approach when using limited data. Several current studies involving non-data-driven algorithms and natural examples are also discussed and certain alternative approaches are suggested.