Subscribers
196 000
YOUTUBE SHOWS "196K subscribers"
CHANNELS / LUIS SERRANO ACADEMY
YouTube channel // numbers taken SEP 06, 2026
Luis Serrano Academy
Luis Serrano Academy has 196 000 YouTube subscribers and 8 152 257 views across the 80 videos we track, counted Sep 6, 2026.
Welcome! I'm Luis Serrano and I love demystifying concepts, capturing their essence, and sharing these videos with you. I prefer illustrations, analogies, and cartoons, rather than formulas (although we don't shy away from the math when needed). The topics I have are machine learning, mathematics (probability and statistics), quantum computing, but I'm open to many others. If you have any topics
▸ Verdict
0.52x
Views per video run at 52% of subscriber count — reach lags the subscriber base.
BASED ON 80 COLLECTED VIDEOS
Views · tracked
8 152 257
SUM OVER 80 VIDEOS WE FOLLOW — NOT LIFETIME
Avg views / video
101 903
OVER 80 TRACKED VIDEOS
Subscriber dynamics
FIRST MEASUREMENT
196 000
SEP 03, 2026
DAILY TRACKING BEGINS ON THE NEXT CRAWL.
GROWTH CHART APPEARS AT 2+ POINTS.
GROWTH CHART APPEARS AT 2+ POINTS.
Views across last 40 videos
Videos · 80
Low Rank Adaptation (LoRA) - How to search for a needle in a much smaller haystack
The attention mechanism in higher dimensions
The world's smallest transformer model
The world's smallest attention mechanism
How neural networks bend space
Retrieval Augmented Generation (RAG), Search, and Vector Databases
Tokenization and Byte Pair Encoding
After AI, what's next for humans? - The pyramid of human evolution
Will AI help us, or make us dependent? - A Tale of Two Cities
Agents, RAG, and Reasoning Models
Strengths and Weaknesses of Large Language Models
Why is KL Divergence not symmetric?
A Visual Guide to Attention Mechanisms in LLMs - Luis Serrano, Data Hack 2025 with @Analytics Vidhya
Quantum superposition and the glove that changes color
Keys, Queries, and Values: The celestial mechanics of attention
Kolmogorov-Arnold Networks (KANs) - What are they and how do they work?
The Kolmogorov-Arnold Theorem
How do Transformer Models keep track of the order of words? Positional Encoding
GRPO - Group Relative Policy Optimization - How DeepSeek trains reasoning models
Universal Approximation Theorem - The Fundamental Building Block of Deep Learning
The Discrete Fourier Transform
What is AdaBoost? Friendly explanation with code!
Discrete Dynamical Systems - Eigenvalues and Eigenvectors
Model that won the 2024 Physics Nobel Prize - Hopfield Networks
The Fast Fourier Transform
Mean, Variance, Skewness, and Kurtosis - Math for ML with Deeplearning.ai
The Stone-Weierstrass Theorem - How to approximate functions
When is a sequence periodic? The Discrete Fourier Transform will tell us
Newton's method for approximating zeros of polynomials - Math for ML with Deeplearning.ai
Can quantum computers break the speed of information?
What are Transformer Models and how do they work?
Proximal Policy Optimization (PPO) - How to train Large Language Models
Reinforcement Learning with Human Feedback (RLHF) - How to train and fine-tune Transformer Models
Direct Preference Optimization (DPO) - How to fine-tune LLMs directly without reinforcement learning
State Space Models (SSMs) and Mamba
Stable Diffusion - How to build amazing images with AI
KL Divergence - How to tell how different two distributions are
Why do we divide by n-1 to estimate the variance? A visual tour through Bessel correction
The math behind Attention: Keys, Queries, and Values matrices
The Attention Mechanism in Large Language Models
