Too Long; Didn't Read
Deep Learning & Artificial Neural Networks: Solving The Black Box Mystery - Roland Hewage. Hewage: No matter how accurate the final outputs are, Artificial Neural Network Lacks explainability of a model in the relevant domain. The idea is called the “information bottleneck” is helping to explain the success of today’s artificial-intelligence algorithms — and might also explain how human brains learn. After a deep neural network has “learned” from thousands of sample dog photos, it can identify dogs in new photos as accurately as people in special cases.