Skip to content
View Dacossti's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report Dacossti

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
Dacossti/README.md

Hi there!👋

Welcome to my AI & Data Science portfolio!

Here, I showcase hands-on experience in machine learning, deep learning, statistical modeling, and AI applications in diverse areas such as robotics.


📊 Projects

1️⃣ Machine Learning & Deep Learning Python Projects

Python NumPy Pandas Scikit-learn TensorFlow Keras PyTorch Matplotlib Seaborn Machine Learning Deep Learning

Description:
A collection of end-to-end machine learning and deep learning projects, including data preprocessing, model training, evaluation, and visualization.

Skills: Python, NumPy, Pandas, scikit-learn, TensorFlow/PyTorch, feature engineering, hyperparameter tuning.

Key Projects:

  • Classification and regression models on public datasets.
  • Neural network experiments exploring architectures and hyperparameters.

Explore the repository →


2️⃣ Life Expectancy Analysis & Age Limit Estimation

R Shiny Plotly HLD HMD IDL Statistics Data Analysis

Description:
Statistical analysis of Life Expectancy trends across genders and countries and assessment of the potential existence of a theoretical limit to human lifespan using Extreme Value Theory (GPD).

Skills: R, R Shiny, Statistical modeling, Data visualisation, Data analysis, plotly, tidyverse.

Key Insights:

  • Trends in life expectancy across countries and demographics.
  • Application of Extreme Value Theory to estimate human lifespan limit.

Explore the repository →


3️⃣ LLM Task Planner for Robotics

Python OpenAI Google Gemini HuggingFace OpenRouter ROS2 Humble Linux WSL Ubuntu AI Robotics Planning

Description:
Integration of Large Language Models with ROS2 to develop a high-level robotic task planner capable of reasoning and autonomous navigation.

Skills: Python, ROS2, Nav2, Linux (Ubuntu/WSL), Motion planning, AI reasoning, System integration.

Key Achievements:

  • Demonstrated autonomous planning capabilities guided by LLM reasoning.
  • Bridges advanced AI concepts with real-world robotics applications.

Explore the repository →


🧠 Hackathons & Research Events

🚀 Simulation-Based Inference (SBI) Hackathon — Grenoble

📍 IMAG Building, Université Grenoble Alpes, France
📅 January 21–23, 2026
🏛️ Organized by SBI4C Chair, MIAI Institute

Bayesian Inference Simulation-Based Inference PyTorch Statistics

Description:
Currently participating in a hands-on hackathon focused on modern Bayesian inference techniques for complex simulators, with an emphasis on likelihood-free inference and uncertainty quantification in scientific models.

Topics & Techniques:

  • Bayesian inference and probabilistic modeling
  • Simulation-Based Inference (SBI)
  • Neural Posterior Estimation (SNPE)
  • Identifiability and uncertainty quantification
  • Inference for dynamical systems (e.g. epidemiological SIR models)

Hands-on Work:

  • Implemented SBI pipelines using PyTorch and the sbi library
  • Performed parameter inference for deterministic and stochastic simulators
  • Analyzed posterior distributions and posterior predictive checks
  • Studied the impact of noise, data limitations, and model identifiability

Skills: Bayesian statistics, probabilistic reasoning, simulation-based modeling, PyTorch, scientific computing, data visualization.

Explore the repository →


💡 Portfolio Summary

  • Strong foundation in machine learning, deep learning, and statistical modeling, with growing expertise in Bayesian inference and probabilistic methods.
  • Hands-on experience applying AI and statistics to real-world and research-driven problems, including simulation-based inference and uncertainty quantification.
  • Proven ability to integrate advanced AI techniques (LLMs) with robotics and autonomous systems.
  • Comfortable working across the full pipeline: modeling, inference, experimentation, and interpretation.
  • Committed to clear documentation, reproducibility, and high-quality technical presentation.

📫 Connect with Me

Pinned Loading

  1. Life-Expectancy-and-Age-Limit Life-Expectancy-and-Age-Limit Public

    A deep study of human longevity using demographic data (HLD, IDL) and Extreme Value Theory to assess the potential existence of a theoretical limit to human lifespan

    R 1 1

  2. Adrien-Sli/Factojulia.jl Adrien-Sli/Factojulia.jl Public

    This project aim to create an equivalent of the well-known FactoMineR in julia where it lack

    Julia 2

  3. LLM-Task-Planner LLM-Task-Planner Public

    An intelligent robotic task planner built on ROS 2 Humble, leveraging Large Language Models for high-level reasoning and Nav2 for autonomous navigation

    Python 2 1

  4. Machine-Learning-and-Deep-Learning-python-projects Machine-Learning-and-Deep-Learning-python-projects Public

    Python projects showcasing machine learning and deep learning techniques, from data preprocessing to model training and evaluation

    Jupyter Notebook 1

  5. Mathematical-Modeling Mathematical-Modeling Public

    Hands-on mathematical modeling labs implemented in Julia and OpenModelica

    HTML 1

  6. Operating-Systems-Linux Operating-Systems-Linux Public

    A series of interesting labs based on linux operating system properties and commands

    TeX 1