Tech
I’ve previously been sceptical about the effectiveness of prompt engineering as a deep specialism, but I’ve changed my views somewhat on “prompt engineering” as a skill set. Which is why today, I enrolled in this short course on ChatGPT prompt engineering. I use ChatGPT mostly when writing code,
Tech
Back propagation is one of those cool machine learning terms that sounds intimidating. And rightly so. The full maths behind it isn’t for everyone. However, knowing the basics is achievable, and I found the video below especially helpful today. I also like this video on gradient descent, which is
Tech
Going through support vector machines today, I realised I needed to refine my understanding of bias and variance. So I went to the machine learning GPT tutor to better understand the terms with regards to their specific use in machine learning. The tutor also provided some cool charts below. On
Tech
The topic of the day was regression trees. They are similar to classification trees but are used to predict continuous values. I only went through a revision primer and can’t say I’ve internalised the full concepts. However, I know the process at a very high level. Machine Learning
Tech
Today I read through how to build a classification tree. There’s a great video on this here from StatQuest. I’m glad we have software that can do the work. Going through it by hand is a hell of a task, even when you have just half a dozen
Tech
About 3 weeks ago (27 Apr) I started the Python for Data Science, AI & Development course. It’s far easier than the Machine Learning with Python course I completed on Day 17. I was able to complete the python course on the side alongside my usual AI readings and
Tech
Today, I returned to decision trees. Even though I was building decision tree models by day 7 of this challenge, I could do with going back to the theory and understanding it better. And that’s what I started doing today. Before starting, we should know that there are two
Tech
I’m about 60% through this workbook, and I have to admit, I really I’m skipping most of the more mathsy bits. I read the Ridge (L2) and Lasso (L1) Regularization sections today and though I didn’t follow the maths fully, at least I came away with the
Tech
Today was a Python practice day. I spent about an hour working through exercises in this book. Python is the most popular language for machine learning and AI so it helps to know it well. It’s also a fantastic generalist language to prototype ideas quickly.
Tech
This morning I made a start on learning about “regularization” in machine learning. When we train sophisticated machine models, sometimes they “overfit” the training data. In the example below from Andrew NG, you can see the third chart on the far right has a blue line (the model) that fits
Tech
I continued working through some Numpy (numerical python) exercises today to better understand why the library is so useful. Turns out, it’s great at dealing with arrays and a variety of numerical computations. Running linear algebra, statistical operations, and other calculations with Numpy is faster and more memory efficient
Tech
I worked through a fast primer on Numpy this morning. Numpy is an open-source Python library for mathematical functions. It’s used often in data science and machine learning so it’s worth knowing the basics. I also enjoyed reading this article which has a moderate view of what large