Vianu AI

The AI club platform at "Tudor Vianu" National College of Computer Science.

Clear lessons, with code snippets

Every module has its lesson: the explanation, the code, and the resources at the end.

import numpy as np

# slow, in pure Python
total = 0
for x in range(1_000_000):
    total += x * x

# fast, vectorized with numpy
v = np.arange(1_000_000)
total = (v * v).sum()

Tips and tricks

Advice from students with real competition experience and results.

S11 · pitfalls

You optimize on the public leaderboard and end up overfitting to it.
Unstratified k-fold on rare classes: some folds don't contain the class at all.
You report accuracy on an imbalanced problem and think the model is good.

Lessons that follow the official syllabus

From basic Python to deep learning. You always see where you are and what's next.

part 1Foundations

S1S2S3S6

part 2Classic machine learning

S8S11S13S14S15S16S17

part 3Deep learning

S18S19S20S21S22S23S24