# Artificial Intelligence

## Transformers: how do they work internally?

Table of Contents Introduction The Transformer is currently one of the most popular architectures for NLP. We can periodically hear news about new architectures and models based on transformers generating a lot of buzz and expectations in the community. Google Research and members from Google Brain initially proposed the Transformer...

## Support Vector Machines (SVM) forÂ Classification

The purpose of this document is to present the linear classification algorithm SVM. The development of this concept has been based on previous ideas that have supported the development of SVM as an algorithm with good generalization capacity, based on an optimization criterion that minimizes complexity; with which we have...

## C# Sudoku Solver

(GitHub Repo: https://github.com/alulema/SudokuSolverNet) I was revisiting a couple of basic AI concepts:  Depth First Search and Constraint Propagation, and I found a very good explanation by Professor Peter Norvig (Solving Every Sudoku Puzzle), I just want to add a couple of simple explanations for a better understanding of the concepts. Constraint...

## TensorFlow High-Level Libraries: TFÂ Estimator

TensorFlow has several high-level libraries allowing us to reduce time modeling all with core code. TF Estimator makes it simple to create and train models for training, evaluating, predicting and exporting. TF Estimator provides 4 main functions on any kind of estimator: estimator.fit() estimator.evaluate() estimator.predict() estimator.export() All predefined estimators are...

## TensorFlow Way for LinearÂ Regression

In my two previous posts, we saw how we can perform Linear Regression using TensorFlow, but Iâ€™ve used Linear Least Squares Regression and Cholesky Decomposition, both them use matrices to resolve regression, and TensorFlow isnâ€™t a requisite for this, but you can use more general packages like NumPy. One of...

## Cholesky Decomposition for Linear Regression withÂ TensorFlow

Several years have already passed since the onset of the Deep Learning boom. I have witnessed impressive achievements like ChatGPT and Midjourney, however, I am still amazed at how traditional methods like Cholesky decomposition remain extremely useful and efficient. Particularly, for tasks like Linear Regression, this method stands out due...

## Linear Least Squares Regression withÂ TensorFlow

Linear Least Squares Regression is by far the most widely used regression method, and it is suitable for most cases when data behavior is linear. By definition, a line is defined by the following equation: For all data points (xi, yi) we have to minimize the sum of the squared...

## Classification Loss Functions (PartÂ II)

In my previous post, I mentioned 3 loss functions, which are mostly intended to be used in Regression models. This time, Iâ€™m going to talk about Classification Loss Functions, which are going to be used to evaluate loss when predicting categorical outcomes. Letâ€™s consider the following vector to help us...