Hey there, fellow learner! I came across a question that resonated with me, and I’d love to share my thoughts on it. The question is: do you really need to understand the mathematics behind machine learning?
I completely understand the confusion. As a junior in high school, you’re already diving into machine learning, working on NLP and ANN, and even collecting your own datasets. That’s impressive! But then you started wondering if you should’ve learned calculus and probability before diving into ML.
Here’s the thing: understanding the math behind machine learning can be useful, but it’s not the only path to becoming proficient in ML. You’ve already gotten a feel for how ML models work, and that’s a great start. However, going back to math can definitely change your perspective and help you appreciate the underlying mechanics.
The question is, do you really need to delve deep into math right now? If you’re mainly focused on collecting, cleaning, and improving data, then building predictive models for hackathons or competitions, you might not need to be an expert in calculus or probability. But, having a basic understanding of these concepts can help you make more informed decisions when working with ML models.
So, what’s the right approach? I think it’s a balance. You can continue learning ML and working on projects while also dedicating some time to reviewing the math fundamentals. This way, you’ll gain practical experience and a deeper understanding of the underlying principles.
Ultimately, it’s about finding a learning path that works for you. Don’t be discouraged if you feel like you’re slowing down; it’s all part of the process. Keep exploring, and you’ll find the right balance for your goals.