Workshop: [SOLD OUT] TensorFlow without a PhD: Deep Learning Guided Codelabs

Location: Cyril Magnin I

Duration: 9:00am - 4:00pm

Day of week: Monday

Level: Intermediate


Please complete the setup instructions before the lab.

This workshop is a guided codelab (two of them actually) through one of the most important frameworks in artificial intelligence and machine learning today, TensorFlow.

The morning starts with presentations and hands-on activities using: TensorFlow and deep learning without a PhD. The afternoon will focus on Recurrent Neural Networks with "Tensorflow, deep learning and Recurrent Neural Networks without a PhD". Each of these codelabs focuses on understanding what is happening behind the maths of a neural network and acquiring the practical engineering skills for training them.

NOTE: As mentioned, this is guided codelab. We will loosely follow (and work in lectures) the online codelabs shown in the abstract. If you’re further along the machine learning path and familiar with Python, there will also be much shorter codelab office hours period during the main part of the conference for people going through the labs by themselves and who have questions.

What you'll learn


  • What is a neural network and how to train it
  • How to build a basic 1-layer neural network using TensorFlow
  • How to add more layers
  • Training tips and tricks: overfitting, dropout, learning rate decay...
  • How to troubleshoot deep neural networks
  • How to build convolutional networks


  • How to build recurrent neural networks
  • RNNs for predictions
  • RNNS for generating sequences

Setup instructions - please prepare before the class:

Morning lab: (this part is NOT using Jupyter notebooks because it features animated visualisation which are not supported in notebooks)

  • install python3, then pip(3)-install tensorflow and matplotlib
  • (on Windows, Anaconda is recommended)
  • Complete installation instructions here. Please TEST your installation as described before the lab.

Afternoon lab (this part IS using Jupyter notebooks):

  • install Python 3, then pip(3)-install jupyter, tensorflow and matplotlib
  • (on Windows, Anaconda is recommended)

Both labs, morning & afternoon: 

  • You will need a git client (Anaconda on windows tip: conda install -c anaconda git)
  • optional but recommended: install the Google Cloud SDK

Speaker: Martin Gorner

Parallel processing and machine learning @Google

Martin is passionate about science, technology, coding, algorithms and everything in between. He graduated from Mines Paris Tech with a major in computer vision, enjoyed his first engineering years in the computer architecture group of ST Microlectronics and then spent the next 11 years shaping the nascent eBook market, starting with the Mobipocket startup, which later became the software part of the Amazon Kindle and its mobile variants. He joined Google Developer Relations in 2011 and now focuses on parallel processing and machine learning (Dataflow and Tensorflow).

Find Martin Gorner at

Proposed Tracks

  • Real-World Data Engineering

    Showcasing DataEng tech and highlighting the strengths of each in real-world applications.

  • Deep Learning Applications & Practices

    Deep learning lessons using Tensorflow, Keras, PyTorch, Caffe across machine translation, computer vision.

  • AI Meets the Physical World

    The track where AI touches the physical world, think drones, ROS, NVidea, TPU and more.

  • Data Architectures You've Always Wondered About

    How did they do that? Real-time predictive pipelines at places like Uber, Self-Driving Cars at Google, Robotic Warehouses from Ocado in the UK, are all possible examples.

  • Applied ML for Software

    Practical machine learning inside the data centers and on software engineering teams.

  • Time Series Patterns & Practices

    Stocks, ad tech/real-time bidding, and anomaly detection. Patterns and practices for more effective Time Series work.