October 2020

The Unreasonable and Unbearable Fluffiness of Deep Learning Models

""although neural networks only work well for an exponentially tiny fraction of all possible inputs, the laws of physics are such that the data sets we care about for machine learning are also drawn from an exponentially tiny fraction of all imaginable data sets..."

Professor Max Tagmark arXiv:160808225 (2017)

 

Like obedient and obsequious slaves, Deep Learning Models (DLM) always produces an answer, regardless of how inappropriate or irrelavent the input data ...

Read more about The Unreasonable and Unbearable Fluffiness of Deep Learning Models