Data driven car diagnostic with Tensorflow & Google Cloud Platform – Maggie Mhanna, Renault Digital

The number of control units, high-tech features, and functionalities used in today’s automobiles have increased tremendously. With such rise in structure complexity and product variety, it becomes difficult for traditional diagnosis techniques to meet the requirements of fault detection and maintenance.

At Renault, we build an AI-powered car diagnostic system operating on cloud in order to improve the diagnosis and maintenance level as well as root cause analysis efficiency.

A neural network algorithm is introduced and key aspects about model building, validation and production using Tensorflow and GCP services are discussed.

Key Takeaways

  • Neural Networks
  • Tensorflow
  • GCP
  • ML production
  • TensorFlow Extended
  • Pipeline Orchestration

Add comment

Highlight option

Turn on the "highlight" option for any widget, to get an alternative styling like this. You can change the colors for highlighted widgets in the theme options. See more examples below.


Instagram has returned empty data. Please authorize your Instagram account in the plugin settings .

Ivana Kotorchevikj

Categories count color


Small ads


  • Matty
  • on rear
  • Traffic lights
  • WoMo
  • Setra presentation
  • endless
  • stand still screening-smoking girl
  • Maya d'Odessa performs her art of make-up
  • Afro-deko-mono

Social Widget

Collaboratively harness market-driven processes whereas resource-leveling internal or "organic" sources.