BookmarkSubscribeRSS Feed
Stewartli
Fluorite | Level 6

Hi guys, 

I try to use SAS Enterprise Miner to build a neural network model. My dataset is relatively small (54 rows x 42 columns). 

SAS EM has Autoneural, neural network, HP neural But I want to control regularization, the number of hidden layers and hidden neurons. Either of three cannot completely meet my demand. Is there any other way to work around it?

I am very new to PROCNNET. Is that correct to use "program editor" in SAS EM to perform PROCNNET? 

One more question. How to use LIBNAME libref if I use SAS on demand for academic?

Please, someone, help me with those questions.

Thank you very much. 

 

 

1 REPLY 1
WendyCzika
SAS Employee

This previous post might help you, it gives examples of how to use PROC HPNEURAL and PROC NEURAL in a SAS programming environment:

 

https://communities.sas.com/t5/SAS-Data-Mining-and-Machine/Deep-learning-in-SAS-Enterprise-miner/m-p...

SAS Innovate 2025: Call for Content

Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!

Submit your idea!

How to choose a machine learning algorithm

Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 1 reply
  • 1102 views
  • 0 likes
  • 2 in conversation