Unfolding the universe of possibilities..

Painting the cosmos of your digital dreams.

Exploring “Small” Vision-Language Models with TinyGPT-V

TinyGPT-V is a “small” vision-language model that can run on a single GPU Summary AI technologies are continuing to become embedded in our everyday lives. One application of AI includes going multi-modal, such as integrating language with vision models. These vision-language

Build Machine Learning Pipelines with Airflow and Mlflow: Reservation Cancellation Forecasting

Learn how to create reproducible and ready-for-production Machine Learning pipelines through a Senior Machine Learning assignment Continue reading on Towards Data Science »

Exploring the Superhero Role of 2D Batch Normalization in Deep Learning Architectures

Internal working and intuitions are explained through simple examples Image created by Author Deep Learning (DL) has been a game-changer in the evolution of Convolutional Neural Networks (CNN) and Generative Artificial Intelligence (Gen AI). Such DL models can extract complex patterns and

Mini-Max Optimization Design of Generative Adversarial Networks (GAN)

Nested bi-level optimization and equilibrium seeking objective Introduction Generative Adversarial Networks (GAN) demonstrated outstanding performance in generating realistic synthetic data which were indistinguishable from the real data. Unfortunately, GAN caught the public’s attention because of its illegit applications, Deep Fake.

Deploy Tiny-Llama on AWS EC2

Learn how to deploy a real ML application using AWS and FastAPI Continue reading on Towards Data Science »

Efficient feature selection via genetic algorithms

Efficient Feature Selection via Genetic Algorithms Using evolutionary algorithms for fast feature selection with large datasets This is the final part of a two-part series about feature selection. Read part 1 here. Brief recap: when fitting a model to a dataset, you

Efficient feature selection via CMA-ES (Covariance Matrix Adaptation Evolution Strategy)

Efficient Feature Selection via CMA-ES (Covariance Matrix Adaptation Evolution Strategy) Using evolutionary algorithms for fast feature selection with large datasets This is part 1 of a two-part series about feature selection. Read part 2 here. When you’re fitting a model to a

PyTorch Introduction — Enter NonLinear Functions

Pytorch Introduction — Enter NonLinear Functions Continuing the Pytorch series, in this post we’ll learn about how non-linearities help solve complex problems in the context of neural networks Neural Networks are Powerful Architectures able to Solve Complex Problems — Image generated by AI In the last

Modeling Dynamical Systems With Neural ODE: A Hands-on Guide

Concepts, case studies, step-by-step implementations Continue reading on Towards Data Science »