Neural Networks - Teradata Vantage

Machine Learning Engine Analytic Function Reference

Product
Teradata Vantage
Release Number
8.00
1.0
Published
May 2019
Language
English (United States)
Last Update
2019-11-22
dita:mapPath
blj1506016597986.ditamap
dita:ditavalPath
blj1506016597986.ditaval
dita:id
B700-4003
lifecycle
previous
Product Category
Teradata Vantageā„¢

NeuralNet function implementation in the ML Engine was completed when neural networks were evolving and applied mostly to small data sets and simple use cases.

Neural network technology has advanced significantly. More advanced neural networks such as Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and Long Short Term memory networks (LSTM) are now the state of the art in image recognition, automated translation and other applications.

Teradata is in the process of implementing a more advanced NeuralNet function, more suitable for large data sets and complex connectivity, which produces more accurate results in less time.

Please contact your account representative or solutions architect, who will contact Teradata Analytics Strategic Offer Management staff. Teradata Analytics Strategic Offer Management staff will help you implement your use case with the right combination of NeuralNet, XGBoost, or other functions.