Skip to main content

Enhancing DNN Explainability in BCI

This project tackled the challenge posed by the opaque nature of Deep Neural Network (DNN) models, especially crucial in safety-driven fields like Brain-Computer Interface (BCI) applications. The primary aim was to unleash the full potential of DNN models, specifically in analyzing EEG signals.

In this initial study, I highlighted the importance of not just relying on quantitative performance but also considering qualitative evaluation. The investigation delved into a key paper in the field, providing a comprehensive analysis as a starting point. I then compared the model against common alternatives, tweaking various hyper-parameters to validate its performance.

To demystify the "black-box," I utilized the Layer-wise Relevance Propagation (LRP) method, revealing insightful details about each model's reliability. LRP proved invaluable in explaining the inner workings of the DNN, making it a useful tool in interpreting complex neural network decisions and enhancing transparency.


Stay curious with me.

Comments

Popular posts from this blog

Public Speaking and Communication Training Application

EmoSpeak Coach, one of my latest creations, is a groundbreaking public speaking and communication training application born out of a personal necessity. As someone deeply invested in effective communication, I created this tool to provide real-time insights into emotional cues and speech patterns during public speaking, aiming to empower individuals on their journey to becoming confident communicators. The inspiration behind EmoSpeak Coach lies in my own experiences, realizing the need for a comprehensive tool that combines face and hands detection, speech-to-text capabilities, and text context evaluation. The goal was to offer users a holistic understanding of their communication style, beyond just emotional expression and speech delivery. The project kicked off with an in-depth analysis of relevant studies, setting the foundation for EmoSpeak Coach. Through meticulous comparisons with alternative models and experimentation with various features, the application evolved to provide use

Chromaid Strandizer

In the fascinating realm of color calibration, a subtle yet impactful tool – the Chromaid Strandizer. This innovative creation, designed to elevate the accuracy of color measurement across diverse industries, caters to the intrinsic need for meticulous color representation. Decoding Chromaid Strandizer At its essence, the Chromaid Strandizer serves as a facilitator for the seamless creation and upkeep of color strand databases. This integral role plays a significant part in ensuring that devices meticulously capture the authentic spectrum of human hair colors. The implications extend far and wide, particularly in industries where the consistency of color is non-negotiable. Unpacking the Significance of Color Calibration Picture a reality where the colors we see are not open to interpretation but are exact and true. Chromaid Strandizer embarks on a mission to manifest this vision by demystifying the intricate art of color calibration. Its impact is particularly profound for professional

Dynamic Learning Tool for Medical Education

Embarking on a transformative journey in medical education, I present a cutting-edge self-learning and self-evaluating platform. Originally built for the aspiring minds of medical students at Sapienza University, this innovation takes the form of a tree-structured questionnaire, introducing a dynamic approach to learning. How It Works Designed to adapt to individual progress, our platform customizes the question flow based on previously selected answers. This dynamic feature not only provides instant feedback but serves as a motivational guide for learners. Users engage with a series of thought-provoking questions, scenarios, and answer choices, witnessing results and explanations unfold in real-time. Active Recall Technique At the heart of this revolutionary platform is an underlying algorithm that employs the powerful Active Recall technique. This technique enhances memory retention by prompting users to actively recall information, contributing to a more robust and enduring understa