Skip to content
View agrija9's full-sized avatar
🐓
El gallo de oro
🐓
El gallo de oro

Block or report agrija9

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
agrija9/README.md

Hi there 👋

I am a machine learning engineer at Epirus in Torrance, California. I am in charge of modeling radio-frequency power amplifiers using neural networks with applications to RF design, RF simulations, digital pre-distortion and other microwave systems.

I was a machine learning researcher at the German Research Center for Artificial Intelligence (DFKI) (Robotics Innovation Center (RIC)) in Bremen, where I applied self-supervised learning techniques to underwater sonar and camera images focusing on underwater robot navigation and perception. Prior to that, I worked as a machine learning researcher at the Fraunhofer Institute for Algorithms and Scientific Computing (SCAI) in Bonn, where I applied generative modeling to time series for unsupervised anomaly detection and 3D reconstruction of turbulent flows. I obtained my M.Sc. in Autonomous Systems from the University of Applied Sciences Bonn-Rhein-Sieg (Germany) and my B.Sc. in Physics from the Universidad Autonoma de Baja California (Mexico), I wrote my B.Sc. thesis at the National Metrology Institute of Germany (PTB) in the field of Trapped-Ion Quantum Engineering.

My research interests lie at the intersection of machine learning, optimization, and statistical modeling with broad applications to computer vision, time series, and telecommunications.

Pinned Loading

  1. ssl-sonar-images ssl-sonar-images Public

    Code for our paper Self-supervised Learning for Sonar Image Classification [CVPR 2022]

    Jupyter Notebook 30 4

  2. Wind-Turbine-Anomaly-Detection-VRAE Wind-Turbine-Anomaly-Detection-VRAE Public

    Code for paper "Anomaly Detection of Wind Turbine Time Series using Variational Recurrent Autoencoders."

    Python 8 2

  3. Deep-Unsupervised-Domain-Adaptation Deep-Unsupervised-Domain-Adaptation Public

    Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E. Evaluated on benchmark dataset Office31.

    Python 81 22

  4. Convolutional-VAE-for-3D-Turbulence-Data Convolutional-VAE-for-3D-Turbulence-Data Public

    A Convolutional Variational Autoencoder (CVAE) for 3D CFD data reconstruction and generation.

    Python 32 3

  5. Avalinguo-Dataset-Speaker-Fluency-Level-Classification-Paper- Avalinguo-Dataset-Speaker-Fluency-Level-Classification-Paper- Public

    Code for paper "Speaker Fluency Level Classification using Machine Learning Techniques."

    Jupyter Notebook 17 6

  6. DLT DLT Public

    A simple python implementation of the normalized DLT algorithm

    Python 10 3