Implementation of Deep Learning algorithm from scratch
-
Updated
Apr 21, 2018 - Jupyter Notebook
Implementation of Deep Learning algorithm from scratch
Jupyter notebook implementing an efficient machine learning method to classify flowers from the Iris data set.
In this project, I implement a softmax classifier and a K-nearest-neighbor algorithm from scratch and train them. I do not use any DL library, only classic math libraries are required (numpy, math, mathplotlib...).
Applying a softmax based neural network to predict customer category
"This program trains a model using 'SVM' or 'Softmax' and predicts the input data. Loss history and predicted tags are displayed as results."
MITx - MicroMasters Program on Statistics and Data Science - Machine Learning with Python - Second Project
Image Classification pipeline for CIFAR-10 dataset based on K-NN, Svm, Softmax and 2-layer Neural Net Classifiers
Classify an email as a ham or a spam.
Just exploring Deep Learning
MNIST Handwritten Digits Classification using Deep Learning with accuracy of 0.9944
Distributed DP-Helmet: Scalable Differentially Private Non-interactive Averaging of Single Layers
Introduction to neural networks
rede neural totalmente conectada, utilizando mini-batch gradient descent e softmax para classificação no dataset MNIST
Classifier Iris dataset with softmax from scratch
Algorithms for logistic regression, including regularization, soft-max loss and classifier
KNN, SVM, Neural network for image classification
Code Snippets for Sentiment Analysis Related Operations
My attempt to implement a generic deep learning platform using Python
Add a description, image, and links to the softmax-classifier topic page so that developers can more easily learn about it.
To associate your repository with the softmax-classifier topic, visit your repo's landing page and select "manage topics."