Skip to content
View ljacquin's full-sized avatar
🎯
Focusing
🎯
Focusing
Block or Report

Block or report ljacquin

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
ljacquin/README.md

Hello 👋, I'm Laval Jacquin

linkedin

Happy to meet you !

Looking for information about me ? Here is what you need to know :

  • My background : I am a statistician and machine learning professional by education, with a background in mathematics and research.

  • My passion : solving data science problems from theory to practice - and vice versa ! - using languages and technologies such as OpenCV, Python, TensorFlow, Keras, R, Shiny, SQL, AWS, Docker, Kubernetes etc., in fields such as the manufacturing industry, energy, the medical sector, agronomy, etc. I am used to develop new statistical & machine learning methods, or to apply state of the art techniques from statistics, machine and deep learning (e.g. Bayesian & Frequentist approaches, Kernel methods, Ensemble methods, Deep-NN, Conv-NN, etc.).

  • What I have achieved so far :

    • I developed the Maintenance Factory SaaS suite, for one of my companies named CYM, which performs real-time analyses using machine, sensor or telemetric data and aims at reducing costs and increasing production within the manufacturing intelligence and predictive maintenance framework.

    • I developed the Prio Retino+ SaaS approach, based on deep convolutional neural networks, which allows automated referable diabetic retinopathy, maculopathy, and glaucoma detection. This approach has been benchmarked with another approach cleared by the FDA in the USA and allows ; 1) fast, 2) massive and 3) regular screening and follow-up of patients. The Prio Retino+ SaaS is currently used by a World Health Organization (WHO) Center in Dakar

    • I developed the CRAN package KRMM for solving "Reproducing Kernel Hilbert Space" (RKHS) regression, used by teams of INRA and CIRAD for genomic prediction and analyses, which competes with current implementations of SVM, random forests and neural networks within the omic framework.

    • I supervised an amazing team of data scientists at OKP4 where we develop many AI based services, for a decentralized protocol, which will allow data sharing and new knowledge creation

  • What I am doing currently : I am the Chief Technology Officer (CTO) of a company named GAIHA which offers AI SaaS solutions, which are scientifically and clinically validated cutting edge technologies, for:

    • referable diabetic retinopathy, its level of severity, and maculopathy detection based on fundus images

    • referable glaucoma detection based on fundus images

    • early breast cancer detection based on blood sample and anthropometric measurements

🔧 Technologies in which I'm well versed

Linux Linux Python scikit-learn Keras pytorch Tensorflow R Shiny MySQL AWS Elastic Search Docker

Pinned

  1. ljacquin ljacquin Public

    1 1

  2. KRMM KRMM Public

    Solves kernel ridge regression within the the mixed model framework. All the estimated components and parameters, e.g. BLUP of dual variables and BLUP of random predictor effects for the linear ker…

    R 1

  3. khamix khamix Public

    Kernelized HAplotype-based MIXed model association mapping (KHAMIX)

    R 4

  4. beagle_v4.0 beagle_v4.0 Public

    This repository provides a generic shell script, the Beagle 4.0 executable, and additional utilities designed to streamline the imputation process.

    Shell 1

  5. refpop refpop Public

    This repository contains the refpop R scripts for achieving reproducible results, according to the FAIR principles.

    R 1

  6. axone-protocol/docs axone-protocol/docs Public

    📜 Axone documentation portal (built with Docusaurus).

    SCSS 37 20