PinnedGreg Postalian-YrausquininTowards AINeural Networks: Basic Theory and Architecture typesIn this story, I would like to attempt to review and explain, at a high level and trying to use simple language, the theoretical…Jun 13Jun 13
PinnedGreg Postalian-YrausquininTowards AIUsing NLP (Doc2Vec) and Neural Networks (with Keras): Removing Hate Speech and Offensive TweetsThis is a great example of how more than one ML step can be used to achieve a goal.Jun 3Jun 3
PinnedGreg Postalian-YrausquininTowards AIConvolutional Neural Networks in PyTorch: Image ClassificationIn this exercise I will use the PyTorch package to build a convolutional neural network with the intention of training a model to classify…Jun 4Jun 4
PinnedGreg Postalian-YrausquininTowards AIUsing Neural Networks with Pytorch to Predict fail of Automatic RecoveryThis exercise is part of aproject implemented on a hardware system. The system has automatic doors that allow to be recovered when they…Jun 31Jun 31
PinnedGreg Postalian-YrausquininTowards AINLP, NN, Time series: Is it possible to predict oil prices using data from Google Trends?Nov 7, 2023Nov 7, 2023
Greg Postalian-YrausquininTowards AIUnderstanding the Transformer ArchitectureReviewing what has been published about the Transformer (which is a lot) we can see a ton of cases and examples of applications for this…Aug 29Aug 29
Greg Postalian-YrausquininTowards AIBayesian analysis and decision theory: application to determine a decision point for classification…A dilemma often presented in classification problems where the output is a number is determining the cutout point between the categories…Jul 18Jul 18
Greg Postalian-YrausquinData visualization: Tableau / Power BI / QuickSightIn this article I will try to showcase examples of dashboards designed in Tableau, Power BI (part of the Microsoft ecosystem) and…Jun 17Jun 17
Greg Postalian-YrausquinNeural networks: encoder-decoder example (autoencoder)The autoencoder is an architecture of neural networks that consists of the implementation of an Encoder network, which transforms the…Jun 11Jun 11
Greg Postalian-YrausquinGAN: training a Generative Adversarial Network for image generationFor this exercise I will train a Generative Adversarial Network to general images based on samples from German traffic signals.Jun 10Jun 10