The last two weeks have been a whirlwind of learning. Not only have I been developing an understanding of how machine learning models make predictions, but I've also been learning how to manage an independent research project. This has meant staying self-motivated, creating a realistic timeline, and figuring out the best way to structure my work.

During the first week, I learnt how to build my own dataset and train a machine learning model to predict the current in an electrical circuit. There were plenty of challenges along the way, particularly with my limited Python experience and my lack of knowledge about machine learning. It was a difficult start, but over the past week I've spent a lot of time exploring how neural networks actually work. The more I've learnt, the more fascinated I've become. Understanding what is happening inside these models has also made me realise that AI is much less of a "black box" than I had imagined.

One of the biggest challenges was deciding on the focus of my research. AI is such a broad field that it's easy to come up with ideas that would take years rather than six weeks to investigate. I considered projects involving physics, engineering, economics and image recognition before taking a step back and thinking about where I could make the most progress. I eventually decided to focus on electrical circuits, as this is an area I'm already familiar with and one where I believe I can gain the deepest understanding of what machine learning is actually learning.

I'm looking forward to starting week three because I now have a much clearer direction for my project. With the foundations in place, I'm excited to begin refining my research question rather than just learning the tools needed to investigate it.