A Deeper Understanding of Deep Learning
Deep learning should not work as well as it seems to: according to traditional statistics and machine learning, any analysis that has too many adjustable parameters will overfit noisy training data, and then fail when faced with novel test data.
Deep learning should not work as well as it seems to: according to traditional statistics and machine learning, any analysis that has too many adjustable parameters will overfit noisy training data, and then fail when faced with novel test data.
analysis, machine learning, traditional statistics, deep learning, novel test data, noisy training data, many adjustable parameters
