I went quiet for a few days
Not because I stopped learning
But because I was heads down studying ๐
Back now and we're not slowing down
Activation Functions, Backpropagation, NLP, LLMs and more coming ๐ฅ
Did you miss the AI breakdowns? ๐
#AI #LearnInPublic
10
ChatGPT, self driving cars, face recognition
They all have one thing in common
Deep Learning ๐งต
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 ๐ฅ
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)))) ๐คฏ
Drop a ๐ฅ if this clicked
#AI #LearnInPublic
17
2 weeks of learning AI in public done โ
What I've covered so far:
๐ค What AI actually is
๐ง Neural Networks
๐ Supervised vs Unsupervised
โ๏ธ Bias vs Variance
๐ Loss Functions & more
And I'm just getting started
Drop a ๐ฅ 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 ๐งต
#AI #LearnInPublic
1
33
Common Loss Functions:
๐ Mean Squared Error โ for predictions (house prices)
๐ง Binary Cross Entropy โ for yes/no decisions (spam or not)
๐ฏ 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 ๐ฅ 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 ๐งต
#AI #LearnInPublic
1
42
See how it connects?
โ High Bias = Underfitting
โ High Variance = Overfitting
โ
Low Bias + Low Variance = perfect model
The goal is always:
Consistent AND accurate
Like an archer hitting the bullseye every single time ๐ฏ
1
34
Bias vs Variance is one of the most important concepts in ML
Once it clicks everything else makes sense
Drop a ๐ฅ if the archer analogy helped
#AI #LearnInPublic
43
