The Test Tribe 25th Virtual Meetup

Hello Testers,

After the passionate response on one of our past offline events, we’re here to bring you all together for one more time.

We’ve brought The Test Tribe 25th Virtual Meetup to all of you!

Excited To Know When It’s Happening?

Date: 27th Jan 2024

Time: 11:00 AM - 1 PM IST

Duration: 2 Hours

A special thank & huge shoutout to Browserstack, Our exclusive sponsor for all community events, and premier sponsor for Conferences.

Season #1: Kick-start your API Testing journey with Postman

We can set up a Postman collection with 5 Essential HTTP methods in Postman, along with API documentation, which is a set of human-readable descriptions for API setup and API details.

Adding the right assertion to validate HTTP responses in the API tests also allows us to run the test collections from the command line using the Newman CLI.

At the end of the session, participants will be able to create an API test, and they will be able to make appropriate test assertions and generate a dashboard-style summary report.

About Speaker:
Ganesh Manoharan, QA Test Engineer at TransUnion 

I am working as a test engineer at Transunion with a decade of experience in quality assurance. I have been involved in different areas of testing, like functional, automation, API, and load testing, with the following domain knowledge: Insurance, logistics, health care, and fintech.

Session #2: White box testing of AI models

White box testing of AI models is a comprehensive approach to testing where the internal structure and workings of the model are thoroughly examined, as opposed to just evaluating the output based on given inputs. This method is particularly crucial in the realm of AI and deep learning, where the complexity and opacity of models can often lead to unexpected behaviors or hidden biases. White box testing involves techniques like neuron coverage analysis, which assesses how much of a neural network is activated during testing, and sensitivity analysis, which evaluates the model’s response to slight variations in input. It also includes visualizing internal activations and filters, especially in convolutional neural networks, to understand what features the model is learning and focusing on.

The practice is essential not only for ensuring the accuracy and efficiency of AI models but also for confirming their reliability, fairness, and transparency. By employing white box testing, developers and data scientists can identify and mitigate potential biases in the model, understand and improve the model’s decision-making process, and ensure that the model performs well under a wide range of conditions. This approach is increasingly important as AI systems become more prevalent in critical and everyday applications, where their decisions can have significant impacts. The session on white box testing of AI models will equip participants with the knowledge and tools to effectively scrutinize and enhance their AI models, ensuring they are robust, fair, and aligned with ethical standards.

Key takeaways:

1. Understanding of Internal Model Mechanics: Attendees will gain insights into how AI models, especially deep learning networks, function internally. This includes knowledge of neuron activation, layer functions, and the importance of model interpretability.

2. Skills in Robustness and Reliability Testing: They will learn techniques to assess and improve the robustness and reliability of AI models, such as testing with adversarial examples, sensitivity analysis, and neuron coverage metrics.

3. Awareness of Bias and Fairness in AI: The session will highlight the importance of testing for biases in AI models, ensuring that the models are fair and do not perpetuate or amplify existing biases.

4. Practical Tools and Techniques: Participants will be introduced to practical tools and methodologies for white box testing, such as gradient checking, activation visualization, and debugging tools, which they can apply in their AI development workflows.

About Speaker:
Toni Ramchandani, Vice President at MSCI Inc.

About The Test Tribe:

The Test Tribe is a leading global Software Testing Community (proudly Asia’s Largest) turned EdTech Startup. Started in 2018 with a mission to give Testing Craft the glory it deserves while we co-create Smarter, Prouder, more confident Testers.

We take pride in creating unique global Events, Online Community spaces, and eLearning platforms where Software Testers across the globe collaborate, learn and grow.

With around 230 Software Testing Events like Conferences, Hackathons, Meetups, Webinars, etc., and with other Community initiatives, we have reached a global footprint of over 80K+ Testers.

We intend to be a one-stop destination of choice for Testers across the globe for their upskilling and community needs.

Check out our upcoming Events list here

Join thousands of other Testers in the community - Discord Community