cancel
Showing results for 
Search instead for 
Did you mean: 
Machine Learning
Dive into the world of machine learning on the Databricks platform. Explore discussions on algorithms, model training, deployment, and more. Connect with ML enthusiasts and experts.
cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

imgaboy
by New Contributor III
  • 30143 Views
  • 9 replies
  • 6 kudos

Spark with LSTM

I am still lost on the Spark and Deep Learning model.If I have a (2D) time series that I want to use for e.g. an LSTM model. Then I first convert it to a 3D array and then pass it to the model. This is normally done in memory with numpy. But what hap...

  • 30143 Views
  • 9 replies
  • 6 kudos
Latest Reply
JohnyBe
New Contributor II
  • 6 kudos

Same problem as @imgaboy here, is the solution was to save into table our inputs after formating them ready to feed the lstm and just turn 2d to 3d via datagenerator??

  • 6 kudos
8 More Replies
self-employed
by Contributor
  • 2985 Views
  • 1 replies
  • 3 kudos

Resolved! Is the machine learning part of "Apache Sparkâ„¢ Tutorial: Getting Started with Apache Spark on Databricks" missing or no longer available?

I am following the Apache Sparkâ„¢ Tutorial. When I finish the data set part and want to continue the machine learning part. I found the page is empty. The next section after machine learning is fine. So I guess there must be a url mismatching.The url ...

  • 2985 Views
  • 1 replies
  • 3 kudos
Latest Reply
self-employed
Contributor
  • 3 kudos

I clean the cookie and then the link recovers. So it is an issue about cookie.

  • 3 kudos
MadelynM
by Databricks Employee
  • 1831 Views
  • 0 replies
  • 2 kudos

2021-08-Best-Practices-for-Your-Data-Architecture-v3-OG-1200x628

Thanks to everyone who joined the Best Practices for Your Data Architecture session on Optimizing Data Performance. You can access the on-demand session recording here and the pre-run performance benchmarks using the Spark UI Simulator. Proper cluste...

  • 1831 Views
  • 0 replies
  • 2 kudos
Labels