Project Summery

Neural networks have a wide range of applications, and one of the most intriguing ones is image classification. In this project, we are delving into the world of image classification using various neural networks, with a particular focus on fully connected networks. Our primary objective is to build a model that can take images as input and accurately categorize each image.

Our task revolves around the classification of images from the CIFAR-10 dataset. This dataset is a carefully curated subset of the CIFAR-100 dataset, featuring images from 10 distinct categories. For computational efficiency, we have narrowed our scope to images from the first four categories within this dataset. These images have dimensions of 32 pixels in length, 32 pixels in width, and encompass vivid color representations with their 3 RGB channels.