Red Pill of Machine Learning

By Monica Anderson

I argue that understanding Deep Neural Networks (DNNs) and other ML technologies requires that practitioners adopt a Holistic Stance which is (at important levels) blatantly incompatible with the Reductionist Stance of modern science. As ML practitioners we have to make hard choices that seemingly contradict many of our core scientific convictions. As a result we may get the feeling something is wrong. The conflict is real and important and the seemingly counter-intuitive choices make sense only when viewed in the light of Epistemology. Improved clarity in these matters should alleviate the cognitive dissonance experienced by some ML practitioners and should accelerate progress in these fields.

The strongest hint that a system is Holistic is that the results improve with practice because the system learns from its mistakes. In Machine Learning, a larger learning corpus is in general better than a smaller one because it provides more opportunities for making mistakes to learn from, such as corner cases.

post

Red Pill

Deep Learning Revolution

Artificial Neural Networks

Holism