JPEG + Fourier Transform + Efficient CNN?
An intriguing idea about using JPEG compression to make neural networks learn faster.
I focus on studying how to make current ML models understand their surroundings more efficiently. Here is a list of some projects I've worked on, enjoy.
An intriguing idea about using JPEG compression to make neural networks learn faster.
This is the latest demo to date of our product in a fully operation vehicle manufactoring plant
A quick exercise of coding a classic transformer from zero to get a full understanding of the logic behind it
Some interesting videos of our product in IAA (The biggest mobility show in the world)
Some reflexions on my time as ML Lead at Kopernikus Automotive. I did not update this page for a while, because being involved in all internal projects demands time.
A quick review of Differentiable Renderers, more exactly a dive deep into SoftRas and a line-to-line understanding of the model
A "quick" review of how to derive the Error State - Extended Kalman Filter
Explain and derive the definition of the Generalized Advantage Estimator
An easy, robust and fast solution for the CarRacing-v0 environment
Autonomous Guided Vehicle in an Experimental Autonomous Warehouse
Cross-Convolutional Neural Networks applied to Finance (working on ...)
Agent-based Models applied to transportation
For fun. Define a group and its properties to understand and solve the cube
Gameboy Zero
This is a project that a friend and I came up with when I found out how tedious it is to exchange games through Facebook groups
Platform to help all students to build and manage their curriculum during the undergraduate degree.