In this project, I also implemented a neural network from scratch using only numpy. The purpose of this implementation was to gain a better understanding of neural networks and how gradients flow from downstream to upstream during the training process. I wanted to delve into the inner workings of neural networks and explore concepts such as forward propagation, backpropagation, and gradient descent.
To evaluate the performance of my neural network, I tested it on the CIFAR-10 dataset. This dataset consists of 60,000 labeled images belonging to 10 different classes. By training and testing my neural network on this dataset, I was able to assess its ability to classify various types of images accurately.