Serafina Di Gioia's Projects
Probabilistic Graphical Models
Intermediate and Advanced Software Carpentry tutorial material
Aesara is a Python library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays.
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
Interpretability and explainability of data and machine learning models
đ§âđŤ 50! Implementations/tutorials of deep learning papers with side-by-side notes đ; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), đŽ reinforcement learning (ppo, dqn), capsnet, distillation, ... đ§
A python tutorial on bayesian modeling techniques (PyMC3)
Reproducing the results of the paper "Bayesian Recurrent Neural Networks" by Fortunato et al.
:exclamation: This is a read-only mirror of the CRAN R package repository. bnlearn â Bayesian Network Structure Learning, Parameter Learning and Inference. Homepage: https://www.bnlearn.com/
Python package for learning the graphical structure of Bayesian networks, parameter learning, inference and sampling methods.
:exclamation: This is a read-only mirror of the CRAN R package repository. CAM â Causal Additive Model (CAM)
Causal Discovery for Python. Translation and extension of the Tetrad Java code.
Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.
Causal Inference Course Repository
Code used in the causality course (401-4632-15) at ETH Zurich.
A Python library that helps data scientists to infer causation rather than observing correlation.
Causal Discovering, ModelIng and Reasoning
Code for Bayesian Analysis
A unified interface for the estimation of causal networks
Introductory course in Computational Physics, including linear algebra, eigenvalue problems, differential equations, Monte Carlo methods and more.
Advanced course in Computational Physics, see texbook at http://compphysics.github.io/ComputationalPhysics2/doc/LectureNotes/_build/html/ with an emphasis on computational quantum mechanics, machine learning and quantum computing.
NMA deep learning course
A Code-First Introduction to NLP course
The 3rd edition of course.fast.ai