Dataset MNIST em um formato mais fácil de se trabalhar.

Training SVM models using gradient descent with a learning rate to classify numbers (4 vs 9).

This project involves the implementation of efficient and effective RBF SVC on MNIST data set. The MNIST data comprises of digital images of several digits ranging from 0 to 9. Each image is 28 x 28 pixels. Thus, the data set has 10 levels of classes.

Deep Convolutional Generative Adversarial Network using Keras

Here using various data visualisation techniques likes TSNE and PCA we will try to visualise various kinds of dataset which is one of the most important part of building a machine learning model

Digit recognition fully-connected neural network using the MNIST dataset, with support for batch and stochastic descent.

Demonstration of simple handwritten digit recognition using a neural network in Python. Based on a book by Tariq Rashid. The neural network is able to decipher greyscale 28 x 28 pictures of numerical digits 0-9 with a very high success rate. It uses MNIST data for training and testing but can also be used with other similar data.

تصنيف الصور باستخدام قاعدة بيانات المعهد الوطني للمعايير والتكنولوجيا المعدّلة - إم. نيست MNIST

Neural Net model Visualizer in web using Flask and streamlit

From scratch C++ Neural Network based on MNIST dataset using templated Tensors with SIMD intrinsics

Homework assignments from the course, Data Mining. Topics covered include: data warehousing, Apriori - market basket analysis, decision trees, supervised learning algorithms, and unsupervised learning algorithms.

Handwritten Digit Recognition using Convolutional Neural Networks

This is a project about prediction of numeric value of digit based on the image of a digit.

Digit recognition using MNIST dataset.

Handwritten digit recognition using Logistic Regression

Digit recognition (MNIST dataset) using a fully connected neural network (97+ on test)

Implemented PCA algorithm from scratch on MNIST Dataset. Visualizing the reconstructed images made and comparing them with the original image. Visualizing the residual images by subtracting the reconstructed image from the original image (for different values of Principal components). Finding the reconstruction error (pixel-wise root-mean-square…

Comparsion of Machine Learning optimization algorithms with MNIST dataset