Latest Reading
16 July 2023
A3T: accuracy aware adversarial training
Published by Springer
This weekend I read about the research on identifying a cause of overfitting related to current practices of generating adversarial examples from misclassified samples and a proposed solution through an accuracy aware AT method that generate adversarial example differently for misclassified and correctly classified samples.
Tech Tales: Insights from Everyday Engineering
Tech Tales : The Mystery of the Multiple Emails (Part 2)
This article is a follow-up that delves deeper into race condition and deadlock, how we can simulate them, and how…
The Mystery of the Multiple Emails: A Reactive Java Surprise
I came across an unexpected behavior when triggering an email service. I noticed that the user was receiving the same…
Shift-Left Strategy: Why it is important in AI and MLOps
In software engineering, the Shift-Left strategy involves moving testing, quality assurance, and other critical processes earlier in the development cycle—essentially…