Deep LearningDeep Learning

This extension provides Deep Learning capabilities for execution on CPU and GPU.

This extension provides operators to create Deep Learning models using different types of layers. Networks can be executed both on CPU and on GPU.

Version 0.8.0:

  • Deep Learning on ExampleSets with native model handling
  • Text Handling using Word2Vec
  • Layers:
    • fully-connected
    • dropout
    • batch normalization
    • convolutional
    • pooling
    • global pooling
  • GPU usage
  • History Port (epoch logging)
  • Custom Icons
  • No external requirements (except for GPU)
  • QuickFixes for switching between regression & classification (loss functions)
  • Model Updatability
  • Samples Processes (samples/Deep Learning)

Remarks:

Execution on GPU is currently only available on NVIDIA GPUs in combination with CUDA version 9.1.

This extension uses the java library DeepLearning4J.

No support for 32-bit.


Product Details

Version 0.8.0
File size 783 MB
Downloads 1138 (15 Today)1138 downloads
Vendor RapidMiner Labs
Category Machine Learning
Released 8/7/18
Last Update 8/7/18 1:12 PM
(Changes)
License AGPL
Product web site rapidminer.com
Rating 0.0 stars(0)

Comments

The data parsing problem occurs when a 32-bit Version of RapidMiner Studio or Java is used. Please check the 64-bit version.

Rapid-Labs, 8/8/18 2:24 PM

I only get a "data parsing problem" error even though with all numerical example sets. Is there a fix for this? Thanks...

Gottfried, 8/8/18 12:00 PM
Log in to post comments.