Abstract: When I opened a neural network text book and saw the bunch of math formulas, I felt like "this is not for me". But wait, TensorFlow now provides the high-level API that let you write a few lines of Python code to get started with neural network, without understanding the hard math. Try this codelab to see how machine learning works on your laptop.
This codelab is designed as an easy TensorFlow introduction for non ML experts. All you need to know is how to use Python. It would take about 2 - 3 hours to go through all the sections.
Preparation: setting up the codelab environment with Cloud Datalab (Jupyter Notebook on GCP)
Understanding neural network with TensorFlow Playgroud: See how "neuron" works with Playground demo
Classify Manhattan with TensorFlow: Let's use TensorFlow to train the most basic neural network
Why deep neural network can get smarter?: Why neural network can get smarter? Build your own deep neural network with Playground and see how it works.
Classify MNIST images with TensorFlow: Use TensorFlow to train a neural network to clasisfy handwritten text images.
Bio: Matthias is a data geek, passionate about gaining insights from data. By day, as head of data science at Datatonic, he helps corporations unleashing the power of data using Google Cloud Platform with custom Machine Learning solutions. By night, Matthias is co-organizer of GDG Cloud Belgium, Tensorflow Belgium and is active participant in other data related meetups. He shares his knowledge by organizing/presenting talks and free training sessions.
Head of Data Science at Datatonic