a really rough neuron network training script for 14 * 14 hand written digits recognition

The Human Neocortical Neurosolver (HNN) is a software tool that gives researchers/clinicians the ability to develop/test hypotheses on circuit mechanisms underlying EEG/MEG data.

Streamlit application for generating and detecting deepfakes. Generates deepfakes in audio, image, and video, and detects deepfakes in images. Uses advanced AI models for accurate results.

Harvard University Online Course | CS50-AI | Artificial Intelligence with Python | Project Solution

Web platform allows users to upload CSV files and train a machine learning model using the uploaded data

Stock Price Prediction

CatDogVision is a project for dog and cat image recognition using a neural network, created for fun and education.

An Artificial Intelligence which plays the popular game "Tetris"

Learn about the Neumorphic engineering process of creating large-scale integration (VLSI) systems containing electronic analog circuits to mimic neuro-biological architectures.

Este repositorio se enfoca en el desarrollo de un sistema basado en redes neuronales para detectar emociones en estudiantes universitarios en el Perú. El objetivo principal es mejorar la calidad de la educación y el rendimiento de los estudiantes al proporcionar información inteligente sobre sus emociones utilizando redes neuronales.

I developed a 2D racing car game in Python and implemented a neural network from scratch, training it using genetic algorithm methods.

Breast cancer classification project.

Programa realizado en python simula una ADALINE

Reconocimiento de dígitos (0 al 9) mediante redes neuronales convolucionales y clasificación.

This is a transfered learning model of yolov5 to use computer vision to check the Team Fortress 2 Models

The project for predicting USD value in BYNs. It was created with recurrent neural network. It was uploaded as a PyCharm project.

2-bits XOR logic implementation using Single Neuron using Backpropagation

Development of deep learning models based on convolutional and recurrent neuronal network for classification of arritmia using ECG. After preprocessing the ECG signals, CNN is applied for features extraction, followed by RNN for temporal feature treatment. Furthermore, the created models are compared with models obtained and supported by the lit…

The systematic identification of functional metabolic control mechanisms relies mostly on the integration of data but barely considers the connectivity of the metabolic network. However, recent geometric deep learning approaches show promising performances in the prediction of links in network or graph structures. By using a dream-case in silico…

This is a small view of what I've learned aboout neuronal networks with TensorFlow