Short description for quick search

MNIST Handwritten Digits Classification using 3 Layer Neural Net 98.7% Accuracy

Various methods for Deep Learning, SGD and Neural Networks.

This project explored the Tensorflow technology, tested the effects of regularizations and mini-batch training on the performance of deep neural networks

classify mnist datasets using ridge regression, optimize the algorithem with SGD, stochastic dual coordinate ascent, and mini-batching

Custom implementation of a neural network from scratch using Python

Generic L-layer 'straight in Python' fully connected Neural Network implementation using numpy.

Optimalization – finding parameters of linear regression using various algorithms

3-layer linear neural network to classify the MNIST dataset using the TensorFlow

A basic neural net built from scratch.

Performing gradient descent for calculating slope and intercept of linear regression using sum square residual or mean square error loss function.

Regression models on Boston Houses dataset

Implementação em Python de uma rede neural perceptron de multicamadas (multilayer perceptron) treinada com Mini-Batch Gradient Descent

rede neural totalmente conectada, utilizando mini-batch gradient descent e softmax para classificação no dataset MNIST

Custom multilayer perceptron (MLP)

A machine learning project applying logistic regression for multi-class classification, ETL, model training, and visualization.

Robust Mini-batch Gradient Descent models