Fernando Martínez-López

Fernando Martínez-López

AI/ML 🤖

Research Assistant @ Fordham University

🎶 Jazz Nerd 🎵

Posts by Collection

portfolio

Mini Imagen Study

Exploring Google’s Imagen, I developed ‘Mini Imagen,’ enhancing my expertise in advanced generative AI.

publications

Rediscovering The Particle in a Box: Machine learning regression analysis for hypothesis generation in physical chemistry lab

Published in Journal of Chemical Education, 2023

We an interactive ML activity that utilizes regression analysis to predict the wavelength of maximum absorption for cyanine dyes. The activity employs a dataset of 13 molecular features to train regression models of increasing complexity. This approach effectively guides students towards the particle-in-a-box (PIB) model, fostering a deeper understanding of the underlying molecular properties that govern cyanine dye absorption.

Recommended citation: Thrall E, Martinez Lopez F, Egg T, Lee SE, Schrier J, Zhao Y. Rediscovering the particle in a box: Machine learning regression analysis for hypothesis generation in physical chemistry lab. Journal of Chemical Education; 2023, doi: 10.1021/acs.jchemed.3c00765

Rediscovering Fraud Detection in Bitcoin Transactions Using Machine Learning Models

Published in WF-IoT, 2023

Performance study of ML techniques such as conventional ML models, regular MLP architectures, and graph convolutional networks to accurately detect fraudulent transactions in the Bitcoin Blockchain.

Recommended citation: F. Martinez, M. Rahouti, A. Chehri, R. Amin and N. Ghani, "Rediscovering Fraud Detection in Bitcoin Transactions Using Machine Learning Models," 2023 IEEE 9th World Forum on Internet of Things (WF-IoT), Aveiro, Portugal, 2023, pp. 1-6, doi: 10.1109/WF-IoT58464.2023.10539490.

Integrating Multiple Visual Attention Mechanisms in Deep Neural Networks

Published in COMPSAC, 2023

We introduce PVAN, a novel and efficient convolutional neural network approach that employs parallelized hybrid visual attention. This method not only outperforms existing state-of-the-art techniques but also maintains efficiency.

Recommended citation: F. Martinez and Y. Zhao, "Integrating Multiple Visual Attention Mechanisms in Deep Neural Networks," 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), Torino, Italy, 2023, pp. 1191-1196, doi: 10.1109/COMPSAC57700.2023.00180.

Redefining Cyber Resilience with Dual-Space Prototypical Networks for DDoS Attack Detection

Published in ICCCN, 2024

Our work introduces the Dual-space Prototypical network, a neural network that leverages a unique dual-space loss function to enhance the detection accuracy of distributed denial-of-service (DDoS) attacks, both known and novel patterns, through geometric and angular similarity measures in the latent space, demonstrating outstanding performance, especially on reduced training sets, which is a challenge for standard deep learning architectures.

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.