A Neural Network in SQL Server

  • Comments posted to this topic are about the item A Neural Network in SQL Server

  • i had a tough time building a neural network. i used mathematical functions to 'amplify', update then recast the result prior to output. it seemed the training would never end.

    close to the end, i was thinking of allowing decimal values instead of integer values. i was maybe thinking, with decimal values it would look fuzzy enough to be accurate.

    i had moved on to another company, leaving the project and with a heavy 'agreement of silence' signed just so i could leave clean.

  • Great and unusual article related to database. Would it be possible to share the source code?


  • Very ineresting, and very well explained.

    Looking for the next session - can you share the source ?



  • Thanks for you comments.

    I will elaborate on the code and how it works in an incoming article, where I'll include the training and testing of the network


  • Hi Silvia: Thanks very much for sharing your methodology, and am really interested in reading your next posting! I've had some success emulating NNs in Excel, but scale becomes an issue eventually. Best Wishes, Michael

  • Thank you for sharing! Well written and understandable for me.

    I am just starting to use SQL Server 2005/2008 as a tool specifically for developing data storage design to be used in predictive analysis as the end goal.

    I am very happy to be able to get some insight to the development this early in the journey! MJWehr

  • I am aware that SSAS has full blown Econometrics built into the SSAS package capable of performing more than just neural nets...we're talking a full slate of linear regression/non-linear regression/discrete choice/arima/two-stage least squares/vector auto regression/co-integration...everything you would find in SAS or SPSS.

    At the end of the day, you still need to get the data into the SSAS tool which is amazingly difficult...and why SQL Server is not a first choice among data analysts for handling statistical analytics.

  • I can see that you can do this using SQL server but I fail to see any benefit to using SQL Server rather than writing some code using a normal computer language like C. Surely it is much slower using SQL Server?

  • jacroberts (10/27/2009)

    I can see that you can do this using SQL server but I fail to see any benefit to using SQL Server rather than wirting some code using a normal computer language like C.

    Surely it is much slower using SQL Server?

    First, I take offense at your characterization of SQL as not a "normal computer language" -- unless, of course, you mean that it's above normal. Second, I laugh at your characterization of C as normal in any way. 😛

    On a serious note, sometimes programming isn't about performance, or even about successfully accomplishing a task, but about learning. From the introduction to the article, it's clear that Silvia wasn't trying to create the most efficient or useful neural network, but more interested in how two programming concepts (a relational database and a neural network) might be brought together.

    Also, bear in mind that many organizations can justify a SQL programmer where they can't justify a .NET or C programmer -- and they may benefit greatly from a neural network in SQL.

  • For me, this is exactly why I read the articles posted almost every day, this is the exactly the type of discussions one needs to understand the various facets of what will work under a variety of circumstances


  • I have a newbie question: SSAS has a neural net algorithm. So, obviously it can be produced in SQL Server. How did your results differ from running the SSAS Neural Net algorithm?

  • When comparing the classification matrices of both NN, mine and SSAS, the global error was quite similar (mine was a little higher but not much). The intention is to show these results when advancing in a coming article

    Thanks for the comments!


  • As we know, there are a variety of Neural Network tools out there - and of course some are better than others. One issue with NNs is that by nature, they are a "black box" technology - its not an easy task to conjure causal factors out of a proprietary tool - whether the output be on target or way off the mark. By capturing how the training (and later, validation) goes in a localized and "query able" data model, the door opens to using this potentially valuable metadata in a variety of creative ways in a much broader data model if the results warrant, not to mention being able to benchmark your own implementation in comparison with other implementations you might try. Looking forward to your next post, Sylvia!

  • With all iterative linear algebra code, the primary considerations are speed and numerical stability. Code maintainability can also be an issue.

    What benefits are there on these fronts to doing the NN trick in sql?

Viewing 15 posts - 1 through 15 (of 25 total)

You must be logged in to reply to this topic. Login to reply