Reptile: A Scalable Meta-Learning Algorithm

Re:Reptile: A Scalable Meta-Learning Algorithm by stochastic_monk on Sunday March 11, 2018 @12:43PM (#16563653)

I imagine that’s because it’s difficult for the model to decide which features are important. Understanding my human bias in looking for an intuitive explanation, the “circle” in this example looks most like the circle in the picture it identified as most similar. I imagine salience assignment is difficult without either more examples or injecting prior knowledge.

[ Parent | on HN ]

Re:Reptile: A Scalable Meta-Learning Algorithm by JHonaker on Sunday March 11, 2018 @03:59PM (#16564492)

Yea I was thinking something similar, the alignment of the eyes is also most similar to that class as well.

The reason we find the frown to be most important is our understanding that this is a common symbolic representation of an emotion.

If we were to look at it as just an abstract shape, I think we'd come to the same conclusion as the algorithm though.

[ Parent | on HN ]

Re:Reptile: A Scalable Meta-Learning Algorithm by mortdeus on Sunday March 11, 2018 @10:43PM (#16565904)

Is it really that hard to determine what changes more geometrically?

:) :( :| :O :D :/ ;)

[ Parent | on HN ]

Re:Reptile: A Scalable Meta-Learning Algorithm by mortdeus on Sunday March 11, 2018 @10:50PM (#16565929)

wouldnt the solution be more accurate if you partitioned the picture down into smaller segments and then just use the algorithm on each part?

[ Parent | on HN ]