Predict a certain outcome with an abstraction named TF-learn instead of Tensorflow.


High level Deep learning with TF-learn on top of Tensorflow

  • What is the purpose of this POC: Predict a certain outcome with TF-learn. In this case the toy example of predicting the survivors of the titanic. This shows how to use an abstraction layer (TF-learn) on top of tensorflow.

Link to DEMO or 30s VIDEO of the project


  • What is the benefit for the customer: I might get a prediction based on my data if something happens. Very vague sorry. Needs a business case...
  • What is the benefit for the business: As a business owner I can quickly predict a certain outcome well, without having to engineer a model in tensorflow, which takes more time.


  • How much MD did you use to build it: 1 MD


  • Which data is it based on: Titic survivors csv

Used Technologies

  • Which technologies were used: Tensorflow, tf-learn (automatic learning for tensorflow), scikit-learn


  • Which things could be build with this POC if you had more time: An automated system that predicts certain values. Very vague, sorry.