Google claims near-human accuracy at imitating a person speaking from text

Re:Google claims near-human accuracy at imitating a person s... by ewrcoffee on Wednesday December 27, 2017 @06:08PM (#16018895)

I think the point of machine learning is that such detailed models do not need to be explicitly modeled, but as some implicit layers to learn.

[ Parent | on HN ]

Re:Google claims near-human accuracy at imitating a person s... by rspeer on Wednesday December 27, 2017 @10:50PM (#16020187)

It's better to have the right explicit features in your model than implicit ones. It's just harder to know how to make those features, and to know that they're right, which is part of the appeal of implicit features.

[ Parent | on HN ]