Ridha Chahed

I am a Machine Learning engineer at Oracle Zurich in the MySQL Heatwave team. I am developing MySQL HeatWave cloud service, a fully managed database cloud service on OCI and AWS.

In the spring 2021 I interned at NEC Labs Princeton under the supervision of Eric Cosatto. I worked on developing deep learning models for cell detection on histology images.

I have a MS in Data Science (AI focus) from EPFL, where I was a research assistant for Dr Mary Anne Hartley and a teaching assistant for professor Martin Jaggi (CS433). I have a BS in Communication Systems from EPFL.

Email  /  Twitter  /  Github  /  LinkedIn

Work

I mainly work on Heatwave AutoML a cloud service for in-database machine learning.
I design and develop new machine learning capabilities for Heatwave AutoML notably Generative AI, Retrieval Augmented Generation (RAG) and Recommendation Systems for database systems.
I am currently focusing on the deployment of Large Language Models and Generative AI solutions in the Heatwave Cloud Service.
I'm interested in Deep Learning, Computer Vision, Machine Learning and Natural Language Processing.

Workshop MySQL Heatwave AutoML

A workshop I built and organized at the Applied Machine Learning Days 2024. Automated Machine Learning from Your Database System with MySQL HeatWave Service.

Machine learning with recommender system models in MySQL Heatwave AutoML

Blog post on how to use Recommender system in MySQL Heatwave AutoML.

Demo: Recommender system with MySQL HeatWave AutoML

Demo live of Recommender Systems in MySQL Heatwave AutoML

MySQL Heatwave AutoML technical brief

Overview of features and enhancements included in HeatWave AutoML.

HeatWave ML: Real-Time Intelligence Comes To MySQL

Article reviewing MySQL HeatWave AutoML.

Projects

These include coursework, side projects and unpublished research work.

Learning to play Pong with Deep Reinforcement Learning

Apply Policy Gradient approaches to teach an agent to play the game Pong from the PyGame Learning Environment.

Digit Comparison with Siamese Network

Try out different architectures of neural nets using PyTorch in order to predict a comparison of two handwritten digits.

Deep Learning mini-framework

Implementing modern deep learning models can hardly be done without a proper framework to minimize code duplication and maximise ease of use as well as good structure. In this project, we implemented our own mini-framework and compared our performance with pyTorch’s NN library, from which it was inspired.

Uncovering World Events using Twitter Hashtags

Use temporal information about Twitter hashtags to discover trending topics and potentially uncover world events as they occurred.

Netflix Recommender System

We study the problem of building an efficient recommender system. We are only given access to a subset of users and their ratings, and we aim to recommend new movies by predicting the missing ratings. To this end, we considered a collaborative-based filtering approach along with ensemble methods.

Higgs Boson Detection

We explore and compare different supervised learning algorithms and how they deal with a data-set from CERN in the field of physics to predict the presence of the Higgs Boson.

Design and source code from Jon Barron's website