Neural Nets Optimizing For Imperfect

John Cook describes a paradox with neural nets:

Deep neural networks have enough parameters to overfit the data, but there are various strategies to keep this from happening. A common way to avoid overfitting is to deliberately do a mediocre job of fitting the model.

When it works well, the shortcomings of the optimization procedure yield a solution that differs from the optimal solution in a beneficial way. But the solution could fail to be useful in several ways. It might be too far from optimal, or deviate from the optimal solution in an unhelpful way, or the optimization method might accidentally do too good a job.

Conceptually, this feels a little weird but isn’t really much of a problem, as we have other analogues:  rational ignorance in economics (where we knowingly choose not to know something because the benefit is not worth the opportunity cost of learning), OPTIMIZE FOR UNKNOWN with SQL Server (where we knowingly do not use the passed-in parameter because we might get stuck in a lesser path), etc.  But the specific process here is interesting.

Related Posts

Multi-Threaded R With Microsoft R Client

David Parr shows us how to get started with Microsoft R Client and performs some quick benchmarking: This message will pop up, and it’s worth noting as it’s got some information in it that you might need to think about: It’s worth noting that right now Microsoft r Client is lagging behind the current R version, and […]

Read More

Image Clustering With Keras And R

Shirin Glander shows us how to use R to extract learned features from Keras and cluster those features: For each of these images, I am running the predict() function of Keras with the VGG16 model. Because I excluded the last layers of the model, this function will not actually return any class predictions as it would normally […]

Read More

Categories

October 2017
MTWTFSS
« Sep Nov »
 1
2345678
9101112131415
16171819202122
23242526272829
3031