Trjtdtk

Professor being mistaken for a grad student

It's a yearly task, alright

Can I respond to my Infinite loop with a summon

Make a transparent 448*448 image

Is it possible to upcast ritual spells?

Who is our nearest planetary neighbor, on average?

Informing my boss about nasty remarks about me from a colleague

Force user to remove USB token

Good allowance savings plan?

How to explain that I do not want to visit a country due to personal safety concern?

I need to drive a 7/16" nut but am unsure how to use the socket I bought for my screwdriver

Do I need life insurance if I can cover my own funeral costs?

What has been your most complicated TikZ drawing?

What options are left, if Britain cannot decide?

How is the Swiss post e-voting system supposed to work, and how was it wrong?

Backup with Hanoi Strategy

Getting particular feature using expression in PyQGIS?

Happy pi day, everyone!

How do I hide Chekhov's Gun?

Min function accepting varying number of arguments in C++17

What are some nice/clever ways to introduce the tonic's dominant seventh chord?

Can hydraulic brake levers get hot when brakes overheat?

Why do Australian milk farmers need to protest supermarkets' milk price?

Rules about breaking the rules. How do I do it well?

How Does Sci-Kit Learn Train Regression Neural Networks (MLPRegressor) So Fast?

Can you explain the difference between SVC and LinearSVC in scikit-learn?what is the difference between “fully developed decision trees” and “shallow decision trees”?Neural Net for regression task on images only learning mean of training dataConvolutional Neural Network not learning EEG dataMultioutput regression with MLPRegressor - Does it work?How to improve my self-written Neural Network?different results with MEKA vs Scikit-learn!Why is cross-validation score so low?ML regression poor performancePretrained features return worse results for sklearn classifier/pipeline

1

$begingroup$

Why does using the scikit-learn library's MLPRegressor result in such a boost in training time when compared to constructing the network from scratch? I tried both methods and I found that writing the code from scratch yielded an average training time of ~10 seconds while Sci-Kit Learn trained almost instantly?

neural-network scikit-learn mlp

share|improve this question

asked 19 hours ago

Shrey JoshiShrey Joshi

1164

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  My suspicion would be that Scikit-Learn utilises a lot of numpy, which in turn utilises C (I could be wrong about that!) - a high-performant low-level language.
  $endgroup$
  – bradS
  18 hours ago
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  If I was to code an ANN from scratch in C then do you think it would perform about the same as Scikit-learn (Not that I'll actually do that!)
  $endgroup$
  – Shrey Joshi
  18 hours ago
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  If you are intelligent enough and know how to optimize your code like hell, then Yes, Just check their Source code simple to see :)
  $endgroup$
  – Aditya
  7 hours ago
  
  

  
  
  
  

add a comment | 

1

$begingroup$

Why does using the scikit-learn library's MLPRegressor result in such a boost in training time when compared to constructing the network from scratch? I tried both methods and I found that writing the code from scratch yielded an average training time of ~10 seconds while Sci-Kit Learn trained almost instantly?

neural-network scikit-learn mlp

share|improve this question

asked 19 hours ago

Shrey JoshiShrey Joshi

1164

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  My suspicion would be that Scikit-Learn utilises a lot of numpy, which in turn utilises C (I could be wrong about that!) - a high-performant low-level language.
  $endgroup$
  – bradS
  18 hours ago
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  If I was to code an ANN from scratch in C then do you think it would perform about the same as Scikit-learn (Not that I'll actually do that!)
  $endgroup$
  – Shrey Joshi
  18 hours ago
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  If you are intelligent enough and know how to optimize your code like hell, then Yes, Just check their Source code simple to see :)
  $endgroup$
  – Aditya
  7 hours ago
  
  

  
  
  
  

add a comment | 

$begingroup$

Why does using the scikit-learn library's MLPRegressor result in such a boost in training time when compared to constructing the network from scratch? I tried both methods and I found that writing the code from scratch yielded an average training time of ~10 seconds while Sci-Kit Learn trained almost instantly?

neural-network scikit-learn mlp

share|improve this question

asked 19 hours ago

Shrey JoshiShrey Joshi

1164

$endgroup$

share|improve this question

asked 19 hours ago

Shrey JoshiShrey Joshi

1164

share|improve this question

asked 19 hours ago

Shrey JoshiShrey Joshi

1164

asked 19 hours ago

Shrey JoshiShrey Joshi

1164

asked 19 hours ago

Shrey JoshiShrey Joshi

1164