D

deep learning

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

The VirtuaLearn3D++ open-source scientific software for 3D point clouds.

Image Tagger is an application that predicts an image's tags using deep-learning. It is useful for photographers who want to improve their workflow by auto-tagging images.

Old functions to play with neural networks. Developed in December 2024

Practical tasks on Deep Learning (DL) and Neural Networks (NN). 🤖

Fundamental theory and practice in Machine Learning (ML) and Data Science (DS). 🧮

PDE-based Group Equivariant CNNs for PyTorch

The Konstellation Runtime Engine (KRE) is an open-source software application designed to run, maintain and evolve any kind of Machine Learning and Deep Learning solution in production.

Sistema de inteligencia artificial basado en visión por computadora para la detección y segmentación de latas y botellas

Webpage for the L52+ lab

This project is a re-implementation of FeatureNet using Tensorflow 2. With working segmentation code.

FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer

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

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