Advanced deep learning approaches have been quite successful to solve real world problems related to unstructured data like images, audio-signals and texts. But how often are we able to make best use of these solutions by exercising their benefits at scale? Even when the deep neural network based solutions have made a significant impact in the world of AI and data science, but the key challenge which most organizations face, is bringing their solutions to production. As a matter of fact, until and unless these remarkable but yet complex algorithms are operated at scale, considering production and if these doesn’t have the capability to be integrated with various software applications, these solutions will never be really impactful.

So, for this talk, I will be discussing about various approaches to accelerate deep learning solutions from notebooks or research environment to production environment and how these solutions can be transformed as an enterprise level end to end Deep Learning Solution, which can be consumed as a service by any software application, with a practical use-case example.


Outline/Structure of the Talk

  • Typical Data Science Workflow and impact of deep learning solutions - 2 mins
  • Why do we need a scalable solution? - 2 mins
  • Importance of Process Pipelines - 2mins
  • Importance of an API Layer and User Interface for a scalable solution - 3 mins
  • Deep Learning As A Service - 3 mins
  • How to make the solution sustainable? - 3 mins
  • Importance of Monitoring Layer and Model Performance Metrics - 3 mins
  • Feedback mechanism based on confidence interval - 2 mins

Learning Outcome

Basic Intuition on developing enterprise level deep learning solution for software products

Target Audience

Software Engineers Data Engineers Data Scientists ML/DL Engineers AI Researchers AI Enthusiast

Prerequisites for Attendees

1. Basic Knowledge on Machine Learning and Deep Learning Concepts

2. Basic Knowledge on Software Engineering



schedule Submitted 1 year ago

Public Feedback