Five Machine Learning Paradoxes that will Change the Way You Think About Data
Many famous statistical paradoxes are omnipresent in machine learning workflows.
Paradoxes are one of the marvels of human cognition that are hard to using math and statistics. Conceptually, a paradox is a statement that leads to an apparent self-contradictory conclusion based on the original premises of the problem. Even the best-known and well-documented paradoxes regularly fool domain experts as they fundamentally contradict common sense. As artificial intelligence(AI) looks to recreate human cognition, it’s very common for machine learning models to encounter paradoxical patterns in the training data and arrive to conclusions that seem contradictory at first glance. Today, I would like to explore some of the famous paradoxes that are commonly found in machine learning models.
Paradoxes are typically formulated at the intersection of mathematics and philosophy. A notorious philosophical paradox is known as the Ship of Theseus questions whether an object that has had all of its components replaced remains fundamentally the same object. First, suppose that the famous ship sailed by the hero Theseus in a great battle has been kept in a harbor as a museum piece. As the years go by some of the wooden parts begin to rot and are replaced…
