D

deep learning

Predicting pathogenic potentials of short DNA reads with reverse-complement deep neural networks.

This repo will have all resources, labs, data which I use/d on Kaggle Network

Este proyecto es material de la materia optativa "Fundamentos Matemáticos del Aprendizaje Profundo" dictada por el Departamento de Matemática de la Facultad de Ciencias Exactas y Naturales de la Universidad de Buenos Aires

Benchmarking framework for machine learning with fNIRS

https://doi.org/10.3389/fnrgo.2023.994969

Webpage for the L52+ lab

This code tries to answer the questions: what are the hardest categories to classify in both single label and multi label image classification tasks? Why do these categories present greater difficulty? Could data augmentation change which the worst performing classes are? Are there consistent patterns across both tasks that explain the poorest performing classes? By using LeNet-5, ResNet-18 and DINO ViT deep learning model architectures

Repository of real applications of neural networks coded in Python with TensorFlow/Keras and PyTorch.

This is an implementation of a very simple neural network from scratch.

This project provides a deep learning approach to learn machining features from CAD models using a hierarchical graph convolutional neural network.

Protocol for network and expression integration to identify potential defense gene in host-pathogen interactions

Projet personnel de classification des maladies des feuilles d'arbre. Article technique disponible sur mon blog : https://boulayc.gitlab.io/blog/

PDE-based Group Equivariant CNNs for PyTorch

FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer

This is the unpaired image-2-image and volume-2-volume translation project. It converts images or volumes of an input domain to a target domain using artificial intelligence.

This is a project to train, use and analyze 2D and 3D neural networks for segmentation.

Lifelong learning is a complex topic in machine learning, whether in combination with reinforce- ment learning or other learning methods. There are different approaches for this and one of them are hypernetworks. Hypernetworks have the advantage of having a very large ability to preserve past memories. Recent work attempts to demonstrate the learning ability of multiple tasks with a hypernetwork such as in the combination of reinforcement learning.