This article is very interesting but I am really confused about the edit:
"A few people have pointed out that using the testing set for tuning demands that final measure of effectiveness be doing using a validation test set which is not part of either the training or testing datasets. This is due for the very real potential of over fitting. Also – apparently this technique is called “Hyper-Parameter Optimization.” A helpful commenter over at Hacker News supplied the following resources"
Does that mean there is definitely overfitting going on but it is acceptable for the purposes of the article. That 82.5% accuracy rate has overfitting written all over it.
"A few people have pointed out that using the testing set for tuning demands that final measure of effectiveness be doing using a validation test set which is not part of either the training or testing datasets. This is due for the very real potential of over fitting. Also – apparently this technique is called “Hyper-Parameter Optimization.” A helpful commenter over at Hacker News supplied the following resources"
Does that mean there is definitely overfitting going on but it is acceptable for the purposes of the article. That 82.5% accuracy rate has overfitting written all over it.
Good stuff regardless!