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
Exploring advanced autoencoder architectures for efficient data compression on EMNIST dataset, focusing on high-fidelity image reconstruction with minimal information loss. This project tests various encoder-decoder configurations to optimize performance metrics like MSE, SSIM, and PSNR, aiming to achieve near-lossless data compression.
This project aims to implement AI-driven letter recognition using neural network libraries and the EMNIST dataset. By employing deep learning and data preprocessing, we seek to build a versatile system for accurately identifying letters in both handwritten and printed text, with applications in OCR and document digitization.
2020/2021 sem 2 - Neural Network Individual Assignment Project - EMNIST prediction - Predict and evaluate the output of model trained using multiple MLP model created by using the EMNIST datasets.