Safe AI: Ensuring Robustness and Reliability in AI Systems
|
4 mins read
- safe ai
- ai techniques
- ai ethics
- robustness
Addressing concerns about AI safety, reliability, and bias for a more trustworthy future with AI technology.
Hello, I'm Ebenezer Gelo 👋🏽
Not available for work
I excel in delivering results through end-to-end machine learning solutions. My expertise lies in algorithm development, deep learning frameworks, and model deployment to production. I am particularly passionate about reinforcement learning (RL), natural language processing (NLP), and computer vision (CV).
Download my resumeOffline RL: An Introduction and Current Challenges
|
4 mins read
- offline-rl
- rl
- safe-ai
Learn how Offline RL tackles challenges to train intelligent decision-makers from existing data, even when live experimentation is impossible.
Knowledge Transfer in AI: Importance and Techniques
|
3 mins read
- knowledge transfer
- ai techniques
Learn how knowledge transfer makes AI models more adaptable, enabling them to tackle new tasks and domains effectively.
Explainable AI (XAI): Making Models Transparent
|
3 mins read
- explainable ai
- ai techniques
- ai ethics
Explainable AI (XAI) helps us understand how AI models make decisions, promoting trust, fairness, and responsible use of AI technology.
About Me
Ebenezer Gelo
Junior Data Scientist @ Pygio
MSc Candidate @ Wits University, RAIL Lab
A little about me...
My journey has been deeply rooted in a profound passion for gaming. Growing up in Hawassa, Ethiopia, my early exposure to technology ignited a lifelong fascination with the limitless possibilities it holds. My fascination has since evolved into a focused interest in AGI.
I believe my passion for AI has shaped me into an advocate for the transformative power it holds and I am excited about the prospect of contributing to advancements in the field, bringing about positive change, and furthering the intersection of technology and society.
What am I doing now?
Currently, I am pursuing my MSc in Computer Science. As part of my master’s degree, I am a member of the RAIL(Robotics, Autonomous Intelligence and Learning) lab where I focus on batch reinforcement learning and knowledge transfer in context of safe and explainable AI. This opportunity allows me to apply my skills in a practical, research-oriented environment, further enhancing my understanding and proficiency in my areas of interest.
See what I'm up to now