Fundamentos Matemáticos para Redes Neurais. Perceptrons e Multi-Layer Perceptrons. Deep Learn. Redes Feedforward. Backpropagation. Regularização. Performance. Avaliação do Aprendizado. Tarefas e Arquiteturas de Redes Neurais: Convolutional Neural Networks (CNNs). Modelos Sequenciais: Recurrent Neural Networks (RNNs). Long Short Term Memory Networks (LSTMs). Generative Adversarial Networks (GANs). Transfer Learning. Hopfield Networks. Boltzmann Machine Network. Deep Belief Networks. Deep Auto-encoders. Capsule Networks. Deep Learning para PLN. Pesquisa em Deep Learn. Modelos Open Source. Algoritmos. Plataformas de Hardware e Software. Exemplos.

Informações Básicas:

• Carga horária: 60 horas;
• Pré-requisito: Aprendizado de Máquinas.

Bibliografia Obrigatória:

• GOODFELLOW, Ian et al. Deep learning. Cambridge: MIT press, 2016. Disponível em: http://www.deeplearningbook.org/;
• TALWALKAR, Ameet. Neural Networks and Deep Learning. Neural Networks, n. 1/16, 2015. Disponível em: http://neuralnetworksanddeeplearning.com/;
• ANDREW NG. Machine Learning Yearning. Disponível em: http://www.mlyearning.org/.

Bibliografia Complementar:

• MCCLURE, Nick. TensorFlow machine learning cookbook. 2017;
• PATTERSON, Josh; GIBSON, Adam. Deep Learning: A Practitioner's Approach. O'Reilly Media, Inc., 2017;
• MICHALSKI, Ryszard S.; CARBONELL, Jaime G.; MITCHELL, Tom M. (Ed.). Machine learning: An artificial intelligence approach. Springer Science & Business Media, 2013;
• Abu-Moustafa, Y.S., Magdon-Ismail, M., e Lin H-S. (2012) Learning from data. AMLBook.com;
• Hastie, T., Tibshirani, R., Friedman, J. (2013) The elements of statistical learning. Springer;
• Luiz André Barroso and Jimmy Clidaras and Urs Hölzle. The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines. Morgan & Claypool Publishers (2013).