New answers tagged

0 votes

Evolving artificial neural networks for solving NP problems

Given that neural nets are good at interpolation (but poor at extrapolation), for a given use case it suffices to solve a few billion large problems and feed them to a sufficiently large net. In some ...
user avatar
  • 3,912
0 votes

Evolving artificial neural networks for solving NP problems

Even if P $\neq$ NP, that says nothing about average case complexity. That for any algorithm for solving a NP complete problem must have at least some instances where it takes more than polynomial ...
user avatar
1 vote

What does "Temporal extent" mean?

It's just the ordinary meaning of the words extent and resolution, only applied to time instead of space. You can think of space-time as a kind of a continuous block, instead of just thinking of time ...
user avatar
1 vote

What is meant by the term "prior" in machine learning

In Bayesian statistics, a "prior" represents the beliefs we have before observing some data. Then, after we observe some data, we update our beliefs; those updated beliefs are called the &...
user avatar
  • 141k
0 votes

What is meant by the term "prior" in machine learning

It's roughly any pre-training choices you encode into your model In machine learning a prior is, according to the book "Deep Learning" by Goodfellow, Bengio, and Courville, a probability ...
user avatar
  • 101
1 vote

Is there a good rule of thumb for regularization constants?

Cross-validation is simple and easy to implement. Rather than inventing something new, which might be dubious, I recommend you use cross-validation. It works. There are no formulas for the ...
user avatar
  • 141k
0 votes

Where should I start for making an AI Bot that processes on screen prompts

More generally you should read about deep reinforcement learning.
user avatar
  • 1

Top 50 recent answers are included