Additionally, we can train w/ a negative orthogonality regularizer for the purpose of intentionally generating feature-combinatorics. In other words, we train for the features to point in more of the same direction to at least generate for-sure examples of feature combination.
Additionally, we can train w/ a negative orthogonality regularizer for the purpose of intentionally generating feature-combinatorics. In other words, we train for the features to point in more of the same direction to at least generate for-sure examples of feature combination.