The challenges and gaps in quality assurance (QA) and testing of AI applications have largely remained unaddressed contributing to a poor translation rate of ML applications from research to real world. Unlike traditional software which has a well-defined software testing methodology, ML applications have largely taken an ad hoc approach to testing. ML researchers and practitioners either fall back to traditional software testing approaches, which are inadequate for this domain, because of its inherent probabilistic and data dependent nature, or rely largely on non-rigorous self-defined quality assurance methodologies.
Objective of the tutorial: This tutorial aims to:
- Provide a comprehensive overview of testing of ML applications.
- Provide practical insights and share best practices for testing ML software.
Key takeaways from this tutorial:
- Overview of testing ML applications: how, why, what.
- Tools and techniques available for testing ML applications.
- Practical insights/tips for incorporating testing in your work on testing ML models.
Full workshop schedule is published here: https://hasgeek.com/anthillinside/testing-machine-learning-applications-workshop/schedule
- Industry Machine Learning practitioners
- Solution architects
- Software developers and ML Engineers working on machine learning applications in production
- Software Quality Assurance (QA) and testing professionals who have to test ML applications
- ML researchers (industry/academic)
Prior background knowledge:
To attend this workshop, participants must have:
- Familiarity with ML concepts.
- Basic to intermediate experience in developing ML applications.
- Working knowledge of general software development life-cycle.
- Intermediate coding ability in Python/R/Java/C/C++/Matlab (which you have used for developing ML applications).
This tutorial does not require any prior knowledge in traditional software testing and quality assurance methodologies.
Participants should bring their own laptop to participate in this tutorial. The trainers will provide a list of open source libraries that have to be installed for hands-on exercises before the tutorial session.
About the trainers:
- Sandya Mannarswamy is an independent NLP researcher. She was previously a senior research scientist at Conduent Labs India in the Natural Language Processing research group. Her research career spans over 16 years at various R&D labs including Hewlett Packard Ltd, IBM Research etc.
- Shourya Roy is Head and VP of American Express AI Labs. Shourya holds a Ph.D. in computer science from Indian Institute of Science (IISc), Bangalore.
- Saro Chidambaram is an independent consultant in Machine Learning and AI technologies. Previously, Saro was part of Hewlett Packard Ltd, Microsoft and Oracle, where he led many R&D projects on virtualization, compilers, kernel and big data.
Date: 30 November
Time: 9:30 AM to 3:45 PM
For tickets and other inquiries, email firstname.lastname@example.org or call 7676332020.