N-Shot Learning: Learning More with Less Data

Re:N-Shot Learning: Learning More with Less Data by nkozyra on Saturday August 03, 2019 @02:25PM (#20601827)

"Ugh" is not a substantial rejoinder. It's an apt analogy in my opinion. People keep waiting for AI to break out, and the argument here is it's not alone a product, it's a requisite tool for building them. AI, of course, is dependent on copious quality data, such that it fuels AI.

With what would you disagree?

[ Parent | on HN ]

Re:N-Shot Learning: Learning More with Less Data by skybrian on Saturday August 03, 2019 @02:37PM (#20601894)

Like many memes, it's vivid for no good reason. The only relationship in common is that A depends on B. Everything else about it is misleading.

Data is not fuel, let alone a fossil fuel. It doesn't provide energy and doesn't get used up.

[ Parent | on HN ]

Re:N-Shot Learning: Learning More with Less Data by hirundo on Saturday August 03, 2019 @03:39PM (#20602220)

> It doesn't provide energy

Training a model with data reduces entropy in the model. Isn't a local increase in energy a decrease in entropy?

> ... and doesn't get used up.

With respect to the model, that data was useful before training and not useful after training. Its entropy lowering potential is decreased.

[ Parent | on HN ]

Re:N-Shot Learning: Learning More with Less Data by nkozyra on Sunday August 04, 2019 @07:28AM (#20605820)

Fuel is used as the metaphor here in the respective mechanisms.

[ Parent | on HN ]