Sebastian Hernandez

Harnessing Artificial Intelligence to Drive Business Insights and Innovation

About Me

I am a Systems Engineer and aspiring Artificial Intelligence specialist passionate about transforming ideas into intelligent solutions. My extensive experience with Python and Linux systems and my AI background have enabled me to take on complex projects and implement innovative solutions.

Photo of Sebastian

My Projects

Blog

  • Neural Networs: the fundamental component of modern AI

    Neural Networs: the fundamental component of modern AI

    Neural networks are at the core of modern artificial intelligence, powering everything from image recognition and natural language processing to medical diagnostics and self-driving cars. While they may seem complex due to their mathematical foundations, they rely on fundamental calculus concepts that even someone with a high school diploma can…

    Read more.

  • Optimization: Gradient Descent

    Optimization: Gradient Descent

    Gradient descent is one of the most used algorithms to optimize a function. Optimizing a function means finding the hyperparameter values for that function that give us the best possible outcome. Gradient descent has broad applications, but in this text, we will focus on its use in Machine Learning to…

    Read more.

  • Why you should never use MSE as a loss function for NN classification problems

    Why you should never use MSE as a loss function for NN classification problems

    The MNIST dataset is an extensive database of handwritten digits commonly used to train NN for image processing systems. Each example in the dataset is a 28×28 image normalized in a matrix with the grayscale values for each pixel. The goal for this dataset is to correctly classify the handwritten…

    Read more.

  • Linear regression loss

    Linear regression loss

    Loss is the utility loss when a model makes a prediction. In simple terms, it is the difference between the observed and predicted values . For linear models we could add up the loss for each prediction to find the overall loss value. However, this is not a good practice…

    Read more.