👋 Hello there! I’m Minh Tri.

I am a Ph.D. graduate in Deep Learning looking for an R&D position in AI based in Grenoble or remotely.

Minh Tri LÊ, Ph.D.

Minh Tri LÊ, Ph.D.

Doctor in deep learning

Seeking an R&D role in AI
Available in Grenoble or remotely

Bio

I am a recent Ph.D. graduate in deep learning seeking an R&D position in AI based in Grenoble area or remotely. I am passionnate about AI, innovation, R&D, and software development.

In 2023, I defended my Ph.D. on deep learning for industrial sensor-based applications on the most constrained devices in the state-of-the-art #tinyML with TDK InvenSense and Inria Grenoble Alpes in the Statify research team.
During my Ph.D., I published several papers in international conferences, as well as patents to make deep learning more efficient for tinyML applications.

Learn more about my Ph.D. subject here, or check out this thesis summary.

In 2019, I graduated as an engineer specialized in Artificial Intelligence at the Université de Technologie de Compiègne (UTC). In addition to the last year of engineering course, I also obtained the Double European Master degree EMECIS in Machine Learning & Optimization between the UTC and the Scuola Politecnica di Genova, Italy, to specialize in research.
During my Master thesis, I worked as a research engineer intern in Deep Learning at TDK InvenSense to get a hands-on experience with my Ph.D. subject.

Check out my resume here.

Interests

  • Deep Learning, Machine Learning
  • R&D, Innovation, Prototyping
  • TinyML & All things model compression: Pruning, Quantization, Knowledge Distillation…
  • Edge Inference
  • Traveling, Languages, Interculturality
  • Mountaineering, Hiking, Skiing, Paragliding
  • Videography & Photography

Education

  • Ph.D. in Deep Learning, 2020-2023

    Université Grenoble Alpes

  • MSc. in Eng. in Computer Science & Engineering, Artificial Intelligence, 2019

    Université de Technologie de Compiègne

  • MSc. in Computer Science, Machine Learning & Optimization, 2019

    Scuola Politecnica di Genova

  • MSc. in Computer Science, Machine Learning & Optimization, 2019

    Université de Technologie de Compiègne

Experiences

 
 
 
 
 

Industrial Ph.D Student in Deep Learning for sensor-based applications

TDK InvenSense & INRIA

Jun 2020 – Jun 2023 Grenoble, France

CIFRE Ph.D. contract

  • Demonstrated ability to collaborate and innovate within international R&D teams through patents, and papers in international conferences
  • Delivered two prototypes with live demos for audio, and gesture recognition running a tiny neural network
  • Researched a novel algorithm for flexible parameter precisions down to 1-bit, reducing model size by 50% with acceptable loss
  • Created and developed an industry-standard software to train and deploy neural networks on the most constrained hardware (< 8KB)

Advisors: Etienne De Foras @TDK InvenSense and Julyan Arbel, Statify team @INRIA Grenoble Rhône-Alpes.

Patents:

  • Lê, M. T. & de Foras, E. (2022). One bit quantization for embedded systems. U.S. patent, filed.
  • Ponçot, R., Lê, M. T., de Foras, E., Ataya, A., & Hartwell, P. G. (2022). Method for improved keyword spotting. U.S. patent application, pending.

Publications:


→ Ph.D. thesis
→ Thesis summary

Keywords: Neural Networks, TinyML, Model Compression, Quantization, Edge Inference, Microcontrollers, Sensors, R&D, Innovation, Prototyping, TensorFlow

 
 
 
 
 

Research Engineer Intern in Deep Learning

TDK InvenSense

Feb 2019 – Aug 2019 Grenoble, France

Objectives included:

  • Outperforming current classic algorithms inaccuracy, power consumption & efficiency of the design cycle
  • First application to fingerprints: classification of dry vs wet finger and detection of finger push or pull events

Keywords: Constrained/embedded neural networks, autoML, quantization, TensorFlow

 
 
 
 
 

Web Developer Intern

Das Keyboard, Metadot Corporation

Sep 2017 – Feb 2018 Austin, TX, USA

Development of an application for a cloud connected keyboard.
Objectives included:

  • Improved real-time communication latency with socket connection to receive signals from the cloud to the application in≈30ms
  • Implemented and suggested new features: Dashboards for socket connections and task scheduler (with Angular 5)
  • Manage data coming in and out from the cloud to the application.
  • Collaborated in SCRUM & Kanban agile framework

Keywords: Front end development, Back end development, Angular 4/5, JavaScript, TypeScript, HTML5, CSS3, Bootstrap, Nodejs, Electron, REST API, WebSocket

 
 
 
 
 

Research on data analysis and visualization of educational content for Faq2sciences.fr in a Scenari context

Kelis

Feb 2017 – Jul 2017 Compiègne, France

Preliminary research study for a CIFRE Ph.D. thesis supervised by Thibaut Arribe, Ph.D. @Kelis and Stéphane Crozat, research professor @Université de Technologie de Compiègne.
The goal was to propose and research what states (e.g. test average, variance, behaviors, hesitations…) could be recover from a large database of singular events, to design a learning dashboard for professors to help identifying first-year students difficulties in STEM for Faq2sciences website in a Scenari context. An event can be switching an answer, validate, coming back to previous questions… and contains a set of JSON attributes (e.g. timestamp, event nature, clicks, quizz values…) and may be noisy.
Objectives included:

  • Analyzed data (test results, answering time) using ElasticSearch to understand student progress and behavior (≈75.000 quiz samples)
  • Designed a learning dashboard from the analysis with Kibana and then Plotly, intended for an integration to Faq2sciences website.

Keywords: Research, Aggregation, Event-State recovery, Data analysis, Data visualization, Learning Dashboards, NoSQL

Skills

Deep Learning / Machine Learning

Neural Networks, Machine Learning, Data Science, Statistics, Data analysis & viz, TensorFlow 2, PyTorch, Scikit-Learn, Numpy

Research & Development

Research design, Innovation, Collaboration, Prototyping, Production, Presentation

Software Engineering

Python, C/C++, Software lifecycle, OOP, Git, Bash

Web Development

TypeScript, JavaScript, Angular 5, Bootstrap, HTML5/CSS3, Electron, Travis-CI, REST API

Languages

• French: Native
• English: Fluent
• Italian & Spanish: Intermediate
• Vietnamese, Mandarin & Polish: Beginner

Videography & Photography

Adobe Premiere Pro, After Effect, Lightroom

Contributions