PC97.com - Plus+ Channels for Creators and Shoppers

GRPO - Group Relative Policy Optimization - How DeepSeek trains reasoning models

Serrano.AcademyMay 23, 2025

PT51M57S

Keys, Queries, and Values: The celestial mechanics of attention

Serrano.AcademyMar 15, 2025

74k

PT13M16S

Universal Approximation Theorem - The Fundamental Building Block of Deep Learning

Serrano.AcademyJan 23, 2025

10k

17k

Proximal Policy Optimization (PPO) - How to train Large Language Models

Serrano.AcademyNov 24, 2024

Direct Preference Optimization (DPO) - How to fine-tune LLMs directly without reinforcement learning

Serrano.AcademyNov 23, 2024

PT17M51S

When is a sequence periodic? The Discrete Fourier Transform will tell us

Serrano.AcademySep 25, 2024

3.1k

PT26M6S

State Space Models (SSMs) and Mamba

Serrano.AcademyJul 17, 2024

18k

PT15M31S

Reinforcement Learning with Human Feedback (RLHF) - How to train and fine-tune Transformer Models

Serrano.AcademyFeb 12, 2024

29k

PT44M59S

Stable Diffusion - How to build amazing images with AI

Serrano.AcademyDec 12, 2023

24k

What are Transformer Models and how do they work?

Serrano.AcademyNov 24, 2023

The Attention Mechanism in Large Language Models

Serrano.AcademyNov 23, 2023

PT36M16S

The math behind Attention: Keys, Queries, and Values matrices

Serrano.AcademyAug 31, 2023

348k

Denoising and Variational Autoencoders

Serrano.AcademyOct 31, 2022

A friendly introduction to deep reinforcement learning, Q-networks and policy gradients

Serrano.AcademyNov 24, 2021

Thompson sampling, one armed bandits, and the Beta distribution

Serrano.AcademyOct 29, 2021

Gaussian Mixture Models

Serrano.AcademyOct 29, 2021

PT13M31S

The Beta distribution in 12 minutes!

Serrano.AcademyJun 13, 2021

114k

PT8M39S

The Gini Impurity Index explained in 8 minutes!

Serrano.AcademyFeb 28, 2021

52k

Generative model that won the 2024 Physics Nobel Prize - Restricted Boltzmann Machines (RBM)

Serrano.AcademyNov 24, 2020

Latent Dirichlet Allocation (Part 1 of 2)

Serrano.AcademyNov 24, 2020

A Friendly Introduction to Generative Adversarial Networks (GANs)

Serrano.AcademyNov 24, 2020

Singular Value Decomposition (SVD) and Image Compression

Serrano.AcademyOct 10, 2020

Clustering: K-means and Hierarchical

Serrano.AcademyNov 27, 2019

Principal Component Analysis (PCA)

Serrano.AcademyNov 26, 2019

Naive Bayes classifier: A friendly approach

Serrano.AcademyNov 18, 2019

Linear Regression: A friendly introduction

Serrano.AcademyOct 24, 2019

Featured Results

Will AI help us, or make us dependent? - A Tale of Two Cities

Strengths and Weaknesses of Large Language Models

GRPO - Group Relative Policy Optimization - How DeepSeek trains reasoning models

Keys, Queries, and Values: The celestial mechanics of attention

Universal Approximation Theorem - The Fundamental Building Block of Deep Learning

The Discrete Fourier Transform

Model that won the 2024 Physics Nobel Prize - Hopfield Networks

Kolmogorov-Arnold Networks (KANs) - What are they and how do they work?

Proximal Policy Optimization (PPO) - How to train Large Language Models

Direct Preference Optimization (DPO) - How to fine-tune LLMs directly without reinforcement learning

When is a sequence periodic? The Discrete Fourier Transform will tell us

State Space Models (SSMs) and Mamba

Reinforcement Learning with Human Feedback (RLHF) - How to train and fine-tune Transformer Models

Stable Diffusion - How to build amazing images with AI

What are Transformer Models and how do they work?

The Attention Mechanism in Large Language Models

The math behind Attention: Keys, Queries, and Values matrices

Denoising and Variational Autoencoders

A friendly introduction to deep reinforcement learning, Q-networks and policy gradients

Thompson sampling, one armed bandits, and the Beta distribution

Gaussian Mixture Models

The Beta distribution in 12 minutes!

The Gini Impurity Index explained in 8 minutes!

Generative model that won the 2024 Physics Nobel Prize - Restricted Boltzmann Machines (RBM)

Latent Dirichlet Allocation (Part 1 of 2)

A Friendly Introduction to Generative Adversarial Networks (GANs)

Singular Value Decomposition (SVD) and Image Compression

Clustering: K-means and Hierarchical

Principal Component Analysis (PCA)

Naive Bayes classifier: A friendly approach

Linear Regression: A friendly introduction

Featured Results

Will AI help us, or make us dependent? - A Tale of Two Cities

Strengths and Weaknesses of Large Language Models

GRPO - Group Relative Policy Optimization - How DeepSeek trains reasoning models

Keys, Queries, and Values: The celestial mechanics of attention

Universal Approximation Theorem - The Fundamental Building Block of Deep Learning

The Discrete Fourier Transform

Model that won the 2024 Physics Nobel Prize - Hopfield Networks

Kolmogorov-Arnold Networks (KANs) - What are they and how do they work?

Proximal Policy Optimization (PPO) - How to train Large Language Models

Direct Preference Optimization (DPO) - How to fine-tune LLMs directly without reinforcement learning

When is a sequence periodic? The Discrete Fourier Transform will tell us

State Space Models (SSMs) and Mamba

Reinforcement Learning with Human Feedback (RLHF) - How to train and fine-tune Transformer Models

Stable Diffusion - How to build amazing images with AI

What are Transformer Models and how do they work?

The Attention Mechanism in Large Language Models

The math behind Attention: Keys, Queries, and Values matrices

Denoising and Variational Autoencoders

A friendly introduction to deep reinforcement learning, Q-networks and policy gradients

Thompson sampling, one armed bandits, and the Beta distribution

Gaussian Mixture Models

The Beta distribution in 12 minutes!

The Gini Impurity Index explained in 8 minutes!

Generative model that won the 2024 Physics Nobel Prize - Restricted Boltzmann Machines (RBM)

Latent Dirichlet Allocation (Part 1 of 2)

A Friendly Introduction to Generative Adversarial Networks (GANs)

Singular Value Decomposition (SVD) and Image Compression

Clustering: K-means and Hierarchical

Principal Component Analysis (PCA)

Naive Bayes classifier: A friendly approach

Linear Regression: A friendly introduction

Loading...