That's how we evaluate lossy compression. It's wrong, but close enough. There is no getting around subjective evaluation.
On Thu, Sep 17, 2020, 7:06 PM <[email protected]> wrote: > But a model that thinks 'cat' has a 80% chance of appearing next and 19% > for 'boat' and 1% for 'dog', and the right answer being 'dog', should do > pretty good predicting 'cat' at 80%! > > ? > > Cat is very similar to dog, so it's as if it's saying "dog: 80%". > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/T5031dc71532ea161-Maae77fcf5c53992bd3475346> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5031dc71532ea161-M9c4447392eb465bd45b5473a Delivery options: https://agi.topicbox.com/groups/agi/subscription
