Abstract
Deep Neural Networks have become one of the center pieces in the field of machine learning, mostly due to accuracy, practical applications and efficiency. These algorithms have proven to be the state of the art in solving tasks such as regressions, clustering and image classification. The purpose of this project was to study and implement deep learning applications using one of the most simple and powerful networks: the multilayer perceptron. Therefore, the project started with a theorical approach and built towards the design of an MLP-based deep neural network capable of classifying hand-written digits.
References
LeCun, Y. The MNIST Database of Handwritten Digits. Available at: http://yann.lecun.com/ exdb/mnist/. Last accessed in: 09/07/2019.
Todos os trabalhos são de acesso livre, sendo que a detenção dos direitos concedidos aos trabalhos são de propriedade da Revista dos Trabalhos de Iniciação Científica da UNICAMP.