Responsible deployment of deep learning

This module is the third and final part of the "Neuron Networks and Deep Learning" certificate. The objective is to deploy a responsible solution based on deep learning, focusing on interpretability and social and ethical implications.

OBJECTIVES

This course will give you :

• An understanding of deep neural networks
• Concrete experience with the deployment and hosting of an AI model
• The tools to design responsible deep learning solutions that meet social and ethical challenges.

CONTENT

• 

  Day 1: Interpretability of artificial neural networks

  How to understand and explain what happens in an artificial neural network? Modeling in the form of a “black box”.

  The main concepts covered in this module are: interpretability, action plan and policy of a model, and the Python SHAP and LIME libraries.

• 

  Day 2: Deployment of a deep learning model

  Concrete example of the deployment of a deep learning and focus model on a few specialized frameworks.

  The main concepts covered in this module are: deployment, data science workload and Strealit and FastAPI frameworks.

• 

  Day 3: Responsible deployment of a deep learning model

  Focus on the interpretability of a model and consideration of the social and ethical implications of deep learning.

  The main concepts covered in this module are: deep learning models, interpretability, deployment.