|
|
Atividade
| 89420 - Do Perceptron às Redes Neurais Generativas: A Evolução das Redes Neurais Artificiais |
| Período da turma: | 26/06/2019 a 28/06/2019
|
||||
|
|
|||||
| Descrição: | Conteúdo:
1 Introdução à base biológica das redes neurais 2 Modelo Perceptron simples 3 Função objetivo e de ativação 4 Multilayer Perceptron e Backpropagation 5 Redes Neurais Artificiais e aplicações 6 Processamento de imagens (Filtros e Kernels) 7 RNA + Processamento de imagens 8 Convoluções 9 Redes Neurais Convolucionais e aplicações 10 Untargeted and Targeted Attacks 11 Redes Neurais Adversariais (GANs) Objetivos: 1 Passar aos alunos os conhecimentos fundamentais sobre redes neurais 2 Familiarização com as ferramentas e técnicas comumentemente usadas 3 Conhecimento sobre o funcionamento e diferenças das Redes Convolucionais Metodologia: Aulas expositivas durante os dois dias do minicurso, finalizando as aulas com aulas práticas, aplicando o conteúdo aprendido em aula em aplicações reais das redes neurais. Bibliography 1162633177087867. (2017, December 25). From Perceptron to Deep Neural Nets. Retrieved from https://becominghuman.ai/from-perceptron-to-deep-neural-nets-504b8ff616e Agrawal, A., & Agrawal, A. (2017, September 29). Loss Functions and Optimization Algorithms. Demystified. Retrieved from https://medium.com/data-science-group-iitr/loss-functions-and-optimization-algorithms- demystified-bb92daff331c Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems, 27, 2672-2680. https://arxiv.org/abs/1406.2661 Ian J. Goodfellow. (2016). NIPS 2016 Tutorial: Generative Adversarial Networks. http://arxiv.org/abs/1701.00160 Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481–2495. http://doi.org/10.1109/tpami.2016.2644615 A Beginner's Guide to Multilayer Perceptrons (MLP). Retrieved from https://skymind.ai/wiki/multilayer-perceptron Yanpei Liu, Xinyun Chen, Chang Liu, Dawn Song (2017). Delving into Transferable Adversarial Examples and Black-box Attacks. 5th International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1611.02770 Gupta, V. (2017, October 23). Home. Retrieved from https://www.learnopencv.com/image-classification-using-feedforward-neural-network-in -keras/ Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. http://doi.org/10.1145/3065386 Nielsen, & A., M. (1970, January 1). Neural Networks and Deep Learning. Retrieved from http://neuralnetworksanddeeplearning.com/chap3.html Shafkat, I. (2018, June 1). Intuitively Understanding Convolutions for Deep Learning. Retrieved from https://towardsdatascience.com/intuitively-understanding-convolutions-for-deep-learnin g-1f6f42faee1 Sinha, U. Image convolution examples. Retrieved from http://aishack.in/tutorials/image-convolution-examples/ V, A. S., & V, A. S. (2017, March 30). Understanding Activation Functions in Neural Networks. Retrieved from https://medium.com/the-theory-of-everything/understanding-activation-functions-in-neu ral-networks-9491262884e0 HAYKIN, Simon. Redes Neurais:Princípios e prática. Porto Alegre RS:Bookman, 2001. |
||||
| Carga Horária: |
8 horas |
||||
| Tipo: | Obrigatória | ||||
| Vagas oferecidas: | 40 | ||||
| Ministrantes: |
Lucas Peres Nunes Matias Luis Alberto Rosero Rosero |
 voltar |
|
Créditos © 1999 - 2024 - Superintendência de Tecnologia da Informação/USP |