TensorFlow Tutorial — Part 3

In the previous Part 1 and Part 2 of this tutorial, I introduced a bit of TensorFlow and Scikit Flow and showed how to build various models on Titanic dataset.

In this part, let’s make a more complex model, something that can handle categorical…

Tensorflow Tutorial — Part 2

In the previous Part 1 of this tutorial, I introduced a bit of TensorFlow and Scikit Flow and showed how to build a simple logistic regression model on Titanic dataset.

In this part let’s go deeper and try multi-layer fully connected neural networks…

In response to Stratechery’s take on TensorFlow

Ben Thompson in his excellent Stratechery blog earlier today wrote a piece about how open-sourcing TensorFlow is a great idea. While he makes some very good points, I find myself in a strange place… I’m disagreeing with him for the first time ever.

Thanks!

For similar estimators (e.g. linear models) it will be slower then very optimized version in Scikit Learn. This is due to few reasons: currently the easiest way to feed data to TensorFlow is via feed_dict, which pretty much requires to copy data every time. And also just general fact, that TensorFlow is deep learning…