You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This repository focuses on handwritten digit recognition using the MNIST dataset. It includes implementations of Logistic Regression, MLP, and LeNet-5 in PyTorch, organized into folders for reports, flowcharts, scripts, and notebooks, with detailed instructions for preprocessing and training.
This repository contains a CNN model for handwritten digit recognition with 98% accuracy. Implemented in a Jupyter Notebook, the code is easy to understand, modify, and use for further development, including creating your webpage.
In this notebook, my objective is to explore the popular MNIST dataset and build an SVM model to classify handwritten digits. Here is a detailed description of the dataset.
This notebook demonstrates a neural network implementation using NumPy, without TensorFlow or PyTorch. Trained on the MNIST dataset, it features an architecture with input layer (784 neurons), two hidden layers (132 and 40 neurons), and an output layer (10 neurons) with sigmoid activation.
This Python notebook demonstrates the application of Support Vector Machines (SVM) for classification tasks on the MNIST dataset. The notebook covers data preprocessing, hyperparameter tuning, and dimensionality reduction using PCA.
Built from scratch SVM, Kernel Perceptron and Neural Network implemented to recognize handwritten digits from the mnist dataset. Includes jupyter notebook of code, mnist handwritten digit data and a PDF of the code & results.