Alban Tchikladzé's Projects
I have come to the conclusion that Kolmogorov complexity is not well suited for neural networks. Based on this conclusion, it is necessary to find an adaptation that will satisfy neural networks specificities. To further our research, we will try to find a computable approximation.
A wonderful introduction for you to my coding addiction
:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.
This Vocale Synthesis Algorithm is able to speak french almost as much as you can do, fully trained within less than 10 days
TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
The balance python package offers a simple workflow and methods for dealing with biased data samples when looking to infer from them to some target population of interest.
Code release for ConvNeXt V2 model
2020 - Application WPF de gestion de création de recettes et de commandes de plats
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
I made this code during my first Engineering year at ESILV, it shows a quite astounding emergence of complex behavior when using only simple rules.
:zap: Dynamically generated stats for your github readmes
Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization
Voici le Maitre du Puissance 4. Envie de l'affronter ou de savoir comment il fonctionne ?
Here you can have a look at my data Analysis of the Melbourne Housing Dataset, that I have done during my Big Data Analytics course at Dublin in Griffith College
Deep learning methods for detecting persuasion techniques in memes
Common used path planning algorithms with animations.
Detecteur automatique d'avions sur des images satellite.
PyTorch Project - Voici la fameuse machine de Blotzmann, l'ancêtre des réseaux de neurones artificels. Initialement inventée sous le nom de Harmonium par Paul Smolenski en 1986.
Deep learning with satellite & aerial imagery
Semi-Supervised Learning is one of the most promising advance in IA, here is an example based on the CIFAR-10 Dataset
Build a Jekyll blog in minutes, without touching the command line.
YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite