Hero Image
The Limited Power of AI: Adversarial Attacks & Defenses!

Introduction Is ML truly ready for real-world deployment? Over the last years, state-of-the-art Deep Learning models are highly effective in solving many complex real-world problems — boosting progress in computer vision and natural language processing and impacting nearly every industry. However, these models are vulnerable to well-designed input samples called adversarial examples. With the advance in AI systems, most companies are focusing on increasing AI performance rather than quality and safety.

March 18, 2021 Read
Hero Image
The Far Side of AI: Neuro-Symbolic AI

Key Words: Symbolic AI, Deep Learning, Neuro-Symbolic AI Introduction Artificial Intelligence( AI ) has been witnessing a monumental growth in bridging the gap between the capabilities of humans and machines. Building thinking machines have been a human obsession for decades. Despite, the current advances in AI and ML, concerns about trust, safety, interpretability, and accountability of AI were raised by influential thinkers. In this article, we will discover the next wave of AI systems by introducing the Neuro-Symbolic AI approach.

January 25, 2020 Read