Retrieval Augmented Generation (RAG), Search, and Vector Databases
Serrano.Academy
Retrieval Augmented Generation (RAG), Search, and Vector Databases
19:02
Tokenization and Byte Pair Encoding
Serrano.Academy
Tokenization and Byte Pair Encoding
7:32
Will AI help us, or make us dependent? - A Tale of Two Cities
Serrano.Academy
Will AI help us, or make us dependent? - A Tale of Two Cities
5:20
After AI, what's next for humans? - The pyramid of human evolution
Serrano.Academy
After AI, what's next for humans? - The pyramid of human evolution
6:02
Agents, RAG, and Reasoning Models
Serrano.Academy
Agents, RAG, and Reasoning Models
27:22
Talk about AI Agents live with Miguel Otero, Josh Starmer, Luis Serrano @TheNeuralMaze @statquest
Serrano.Academy
Talk about AI Agents live with Miguel Otero, Josh Starmer, Luis Serrano @TheNeuralMaze @statquest
1:00:39
Strengths and Weaknesses of Large Language Models
Serrano.Academy
Strengths and Weaknesses of Large Language Models
26:03
Why is KL Divergence not symmetric?
Serrano.Academy
Why is KL Divergence not symmetric?
8:51
A Visual Guide to Attention Mechanisms in LLMs - Luis Serrano, Data Hack 2025 with @Analytics Vidhya
Serrano.Academy
A Visual Guide to Attention Mechanisms in LLMs - Luis Serrano, Data Hack 2025 with @Analytics Vidhya
51:47
How to stay relevant in AI
Serrano.Academy
How to stay relevant in AI
2:21
Read papers with Luis - The Illusion (of the illusion) of thinking
Serrano.Academy
Read papers with Luis - The Illusion (of the illusion) of thinking
1:08:17
Live with Gaurav Sen, Josh Starmer, and Luis Serrano!
Serrano.Academy
Live with Gaurav Sen, Josh Starmer, and Luis Serrano!
1:07:09
Can quantum computers break the speed of information?
Serrano.Academy
Can quantum computers break the speed of information?
21:32
Josh Starmer and Luis Serrano Live Q/A from Uphill at Bern! (Moderated by Philip Schläfl)
Serrano.Academy
Josh Starmer and Luis Serrano Live Q/A from Uphill at Bern! (Moderated by Philip Schläfl)
1:01:38
Discrete Dynamical Systems - Eigenvalues and Eigenvectors
Serrano.Academy
Discrete Dynamical Systems - Eigenvalues and Eigenvectors
26:16
Mean, Variance, Skewness, and Kurtosis - Math for ML with Deeplearning.ai
Serrano.Academy
Mean, Variance, Skewness, and Kurtosis - Math for ML with Deeplearning.ai
26:17
The three steps to make a reliable chatbot: Preamble, Fine-tuning, and RAG
Serrano.Academy
The three steps to make a reliable chatbot: Preamble, Fine-tuning, and RAG
1:38
Newton's method for approximating zeros of polynomials - Math for ML with Deeplearning.ai
Serrano.Academy
Newton's method for approximating zeros of polynomials - Math for ML with Deeplearning.ai
10:16
The Stone-Weierstrass Theorem - How to approximate functions
Serrano.Academy
The Stone-Weierstrass Theorem - How to approximate functions
36:45
Keys, Queries, and Values: The celestial mechanics of attention
Serrano.Academy
Keys, Queries, and Values: The celestial mechanics of attention
51:57
Why is ChatGPT so bad at telling jokes (yet so good at writing poems?)
Serrano.Academy
Why is ChatGPT so bad at telling jokes (yet so good at writing poems?)
2:12
Why is DeepSeek so good?
Serrano.Academy
Why is DeepSeek so good?
1:27
Universal Approximation Theorem - The Fundamental Building Block of Deep Learning
Serrano.Academy
Universal Approximation Theorem - The Fundamental Building Block of Deep Learning
13:16
Happy 2025, and thank you for your support!
Serrano.Academy
Happy 2025, and thank you for your support!
0:49
The Kolmogorov-Arnold Theorem
Serrano.Academy
The Kolmogorov-Arnold Theorem
23:00
Kolmogorov-Arnold Networks (KANs) - What are they and how do they work?
Serrano.Academy
Kolmogorov-Arnold Networks (KANs) - What are they and how do they work?
14:20
Live with Jay Alammar, Josh Starmer, and Luis Serrano
Serrano.Academy
Live with Jay Alammar, Josh Starmer, and Luis Serrano
1:07:24
What is AdaBoost? Friendly explanation with code!
Serrano.Academy
What is AdaBoost? Friendly explanation with code!
17:41
How do Transformer Models keep track of the order of words? Positional Encoding
Serrano.Academy
How do Transformer Models keep track of the order of words? Positional Encoding
9:50
Model that won the 2024 Physics Nobel Prize - Hopfield Networks
Serrano.Academy
Model that won the 2024 Physics Nobel Prize - Hopfield Networks
34:54
State Space Models (SSMs) and Mamba
Serrano.Academy
State Space Models (SSMs) and Mamba
26:06
Josh Starmer and Luis Serrano livestream 2 - Double BAM!
Serrano.Academy
Josh Starmer and Luis Serrano livestream 2 - Double BAM!
1:00:18
Why do we divide by n-1 to estimate the variance? A visual tour through Bessel correction
Serrano.Academy
Why do we divide by n-1 to estimate the variance? A visual tour through Bessel correction
37:23
The Attention Mechanism for Large Language Models #AI #llm #attention
Serrano.Academy
The Attention Mechanism for Large Language Models #AI #llm #attention
1:00
Stable Diffusion - How to build amazing images with AI
Serrano.Academy
Stable Diffusion - How to build amazing images with AI
44:59
How Large Language Models are Shaping the Future
Serrano.Academy
How Large Language Models are Shaping the Future
1:02:43
What are Transformer Models and how do they work?
Serrano.Academy
What are Transformer Models and how do they work?
44:26
The math behind Attention: Keys, Queries, and Values matrices
Serrano.Academy
The math behind Attention: Keys, Queries, and Values matrices
36:16
The Attention Mechanism in Large Language Models
Serrano.Academy
The Attention Mechanism in Large Language Models
21:02
The Binomial and Poisson Distributions
Serrano.Academy
The Binomial and Poisson Distributions
26:41
Euler's number, derivatives, and the bank at the end of the universe
Serrano.Academy
Euler's number, derivatives, and the bank at the end of the universe
25:18
Decision trees - A friendly introduction
Serrano.Academy
Decision trees - A friendly introduction
22:23
Thank you for 100K subscribers! I’m planning tons of new content coming soon, so excited!
Serrano.Academy
Thank you for 100K subscribers! I’m planning tons of new content coming soon, so excited!
1:01
How do you minimize a function when you can't take derivatives? CMA-ES and PSO
Serrano.Academy
How do you minimize a function when you can't take derivatives? CMA-ES and PSO
15:04
Denoising and Variational Autoencoders
Serrano.Academy
Denoising and Variational Autoencoders
31:46
Eigenvectors and Generalized Eigenspaces
Serrano.Academy
Eigenvectors and Generalized Eigenspaces
19:18
Thompson sampling, one armed bandits, and the Beta distribution
Serrano.Academy
Thompson sampling, one armed bandits, and the Beta distribution
12:40
The Beta distribution in 12 minutes!
Serrano.Academy
The Beta distribution in 12 minutes!
13:31
The covariance matrix
Serrano.Academy
The covariance matrix
13:57
Gaussian Mixture Models
Serrano.Academy
Gaussian Mixture Models
17:27
Singular Value Decomposition (SVD) and Image Compression
Serrano.Academy
Singular Value Decomposition (SVD) and Image Compression
28:56
Generative model that won the 2024 Physics Nobel Prize - Restricted Boltzmann Machines (RBM)
Serrano.Academy
Generative model that won the 2024 Physics Nobel Prize - Restricted Boltzmann Machines (RBM)
36:58
A Friendly Introduction to Generative Adversarial Networks (GANs)
Serrano.Academy
A Friendly Introduction to Generative Adversarial Networks (GANs)
21:01
You are much better at math than you think
Serrano.Academy
You are much better at math than you think
10:36
Live chat with Luis Serrano!
Serrano.Academy
Live chat with Luis Serrano!
1:30:23
Training Latent Dirichlet Allocation: Gibbs Sampling (Part 2 of 2)
Serrano.Academy
Training Latent Dirichlet Allocation: Gibbs Sampling (Part 2 of 2)
26:31
Latent Dirichlet Allocation (Part 1 of 2)
Serrano.Academy
Latent Dirichlet Allocation (Part 1 of 2)
26:57
Book by Luis Serrano - "Grokking Machine Learning" (40% off promo code)
Serrano.Academy
Book by Luis Serrano - "Grokking Machine Learning" (40% off promo code)
1:01
Serrano.Academy - The art of understanding
Serrano.Academy
Serrano.Academy - The art of understanding
0:43
Naive Bayes classifier: A friendly approach
Serrano.Academy
Naive Bayes classifier: A friendly approach
20:29
Math and OCD - My story with the Thue-Morse sequence
Serrano.Academy
Math and OCD - My story with the Thue-Morse sequence
11:01
Principal Component Analysis (PCA)
Serrano.Academy
Principal Component Analysis (PCA)
26:34
Clustering: K-means and Hierarchical
Serrano.Academy
Clustering: K-means and Hierarchical
17:23
How does Netflix recommend movies? Matrix Factorization
Serrano.Academy
How does Netflix recommend movies? Matrix Factorization
32:46
Deep Neural Networks - USF Data Science Seminar by Luis Serrano
Serrano.Academy
Deep Neural Networks - USF Data Science Seminar by Luis Serrano
57:49
A friendly introduction to Bayes Theorem and Hidden Markov Models
Serrano.Academy
A friendly introduction to Bayes Theorem and Hidden Markov Models
32:46
Shannon Entropy and Information Gain
Serrano.Academy
Shannon Entropy and Information Gain
21:16
A friendly introduction to Recurrent Neural Networks
Serrano.Academy
A friendly introduction to Recurrent Neural Networks
22:44
A friendly introduction to Convolutional Neural Networks and Image Recognition
Serrano.Academy
A friendly introduction to Convolutional Neural Networks and Image Recognition
32:08
A friendly introduction to Deep Learning and Neural Networks
Serrano.Academy
A friendly introduction to Deep Learning and Neural Networks
33:20
Bayes theorem, false positives, and why I'm terrified of going to the doctor
Serrano.Academy
Bayes theorem, false positives, and why I'm terrified of going to the doctor
14:45
Geometric series and my Irish heritage
Serrano.Academy
Geometric series and my Irish heritage
9:15