Category Archives: Artificial Intelligence
Why Does Reinforcement Learning Outperforms Offline Fine-Tuning? Generation-Verification Gap Explained
In the ever-evolving world of artificial intelligence, fine-tuning models to achieve optimal performance is a critical endeavor. We often find ourselves choosing between different methodologies, particularly when it comes to refining large language models (LLMs) or complex AI systems. Two primary approaches stand out: reinforcement learning (RL) and offline fine-tuning methods like Direct Preference Optimization…
What a month! 5 events, 8 awards and 10 new team mates
November was not supposed to be this tectonic and yet here I am, with a huge grin on my face, trying to let all of the impression sink in. This is the list of events I’ve participated in: Event Date Location Prize 1. NASA SpaceApp 2023 Challenge 16th of October 2023 Online – 2. European…
Creating my digital clone from Facebook messages using nanoGPT
As a software developer, I am always on the lookout for exciting new ways to use natural language processing (NLP) to enhance user experiences. Recently, I took on an interesting weekend project: creating a digital clone of myself based on the Facebook messages I’ve sent over the last three years. The idea was inspired by…
Explainable AI – what is it and why should you care?
In most of the cases each model is observed as a black box – data goes in, prediction goes out. The intrinsic details of processing are initially reserved for machine learning researchers in academic circles. Even they don’t know what exactly did the network learn, they can only propose the model architectures and training methods…