Federated Deep Learning in SAAS Applications
ML in Saas Applications becomes exceedingly difficult due to lack to access to customer data. The Customer Data is locked down with no outside access and it presents a huge problem to do ML on this data in a traditional way. The focus of this presentation is to provide alternate solutions to do ML in a distributed fashion.
We will focus on Split Neural Networks - a relatively new distributed ML Technique to solve Data Access issues with a SAAS Application.
We will walk through the motivations behind Split Neural Network approach to ML .
We will go through some concrete examples that are already using this technique.
Outline/Structure of the Demonstration
Machine Learning and Privacy
(Anonymous, Obfuscated, Encrypted) DATA !
Privacy and ML – Techniques
Machine Learning at Healthcare and SAAS applications
Split Neural Network – Introduction
SAAS Use Case – Anomaly Detection
Split NN to rescue
Learning Outcome
Learn the latest world of distributed deep learning techniques.
Target Audience
All Machine Learning Practitioners
Prerequisites for Attendees
Neural Network Fundamentals
Video
Links
schedule Submitted 2 years ago
People who liked this proposal, also liked:
-
keyboard_arrow_down
Dr Hari Krishna Maram - Future of Technology
20 Mins
Talk
Executive
Future of Technology covered trends in technology across the globe and innovation changing the future
-
keyboard_arrow_down
Arun Krishnaswamy - ROI in Data Science
45 Mins
Talk
Executive
Data Science , ML , AI have become buzz words and everyone is into it. Having spent all my career as a ROI Data Scientist - I would like to present my ideas around how to achieve ROI in Data Science.
Data Science can be tricky and he can fall into this Rabbit Hole without destination and the projects become super expensive without much returns - In this talk I will focus on the common pitfalls around Data Science Projects and how to navigate this without any dent to the investments we make towards a data driven world.
Public Feedback