Oyedokun Oluwatobiloba (@devaladey) profile picture

Full-stack dev learning AI in public ๐Ÿง  | HTML CSS JS React Next.js Python & more | Documenting my AI journey daily | Come learn with me ๐Ÿ‘‡

Lagos, Nigeria
Joined May 2022
Photo by Oyedokun Oluwatobiloba (@devaladey)
I went quiet for a few days Not because I stopped learning But because I was heads down studying ๐Ÿ“š Back now and we're not slowing down Activation Functions, Backpropagation, NLP, LLMs and more coming ๐Ÿ”ฅ Did you miss the AI breakdowns? ๐Ÿ‘‡ #AI #LearnInPublic
10
ChatGPT, self driving cars, face recognition They all have one thing in common Deep Learning ๐Ÿงต Let me show you how it actually works #AI #LearnInPublic
1
16
Before Deep Learning โ€” AI was limited 2012 changed everything A Deep Learning model called AlexNet crushed every other model at image recognition The AI world was never the same again That moment started the era we're living in now ๐Ÿ”ฅ
1
15
Deep Learning is not magic It's just layers of math stacked on top of each other running millions of times y = f(f(f(f(x)))) ๐Ÿคฏ Drop a ๐Ÿ”ฅ if this clicked #AI #LearnInPublic
17
2 weeks of learning AI in public done โœ… What I've covered so far: ๐Ÿค– What AI actually is ๐Ÿง  Neural Networks ๐Ÿ“Š Supervised vs Unsupervised โš–๏ธ Bias vs Variance ๐Ÿ“‰ Loss Functions & more And I'm just getting started Drop a ๐Ÿ”ฅ if you've been following along #AI #LearnInPublic
17
How does AI know when it's wrong? One word โ€” Loss Function This is what makes AI actually learn ๐Ÿงต #AI #LearnInPublic
1
33
Common Loss Functions: ๐Ÿ“Š Mean Squared Error โ€” for predictions (house prices) ๐Ÿ“ง Binary Cross Entropy โ€” for yes/no decisions (spam or not) ๐ŸŽฏ Categorical Cross Entropy โ€” for multiple categories (cat, dog, bird) Different problems โ†’ different loss functions
1
59
Without a Loss Function AI has no way of knowing it's wrong It's the feedback mechanism that makes learning possible Drop a ๐Ÿ”ฅ if this clicked #AI #LearnInPublic
29
Why do AI models fail even after training? Two reasons โ€” Bias and Variance This one changed how I think about ML ๐Ÿงต #AI #LearnInPublic
1
42
See how it connects? โŒ High Bias = Underfitting โŒ High Variance = Overfitting โœ… Low Bias + Low Variance = perfect model The goal is always: Consistent AND accurate Like an archer hitting the bullseye every single time ๐ŸŽฏ
1
34
Bias vs Variance is one of the most important concepts in ML Once it clicks everything else makes sense Drop a ๐Ÿ”ฅ if the archer analogy helped #AI #LearnInPublic
43