Full-stack dev learning AI in public 🧠 | HTML CSS JS React Next.js Python & more | Documenting my AI journey daily | Come learn with me 👇
Lagos, Nigeria
Joined May 2022
- Tweets115
- Following11
- Followers7
- Likes106
I went quiet for a few days
Not because I stopped learning
But because I was heads down studying 📚
Back now and we're not slowing down
Activation Functions, Backpropagation, NLP, LLMs and more coming 🔥
Did you miss the AI breakdowns? 👇
#AI #LearnInPublic
ChatGPT, self driving cars, face recognition
They all have one thing in common
Deep Learning 🧵
Let me show you how it actually works
#AI #LearnInPublic
Before Deep Learning — 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 🔥
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)))) 🤯
Drop a 🔥 if this clicked
#AI #LearnInPublic
2 weeks of learning AI in public done ✅
What I've covered so far:
🤖 What AI actually is
🧠 Neural Networks
📊 Supervised vs Unsupervised
⚖️ Bias vs Variance
📉 Loss Functions & more
And I'm just getting started
Drop a 🔥 if you've been following along
#AI #LearnInPublic
How does AI know when it's wrong?
One word — Loss Function
This is what makes AI actually learn 🧵
#AI #LearnInPublic
Common Loss Functions:
📊 Mean Squared Error — for predictions (house prices)
📧 Binary Cross Entropy — for yes/no decisions (spam or not)
🎯 Categorical Cross Entropy — for multiple categories (cat, dog, bird)
Different problems → different loss functions
Without a Loss Function AI has no way of knowing it's wrong
It's the feedback mechanism that makes learning possible
Drop a 🔥 if this clicked
#AI #LearnInPublic
Why do AI models fail even after training?
Two reasons — Bias and Variance
This one changed how I think about ML 🧵
#AI #LearnInPublic
See how it connects?
❌ High Bias = Underfitting
❌ High Variance = Overfitting
✅ Low Bias + Low Variance = perfect model
The goal is always:
Consistent AND accurate
Like an archer hitting the bullseye every single time 🎯
Bias vs Variance is one of the most important concepts in ML
Once it clicks everything else makes sense
Drop a 🔥 if the archer analogy helped
#AI #LearnInPublic