Aucune documentation obligatoire. Les notes de cours seront écrites au tableau et sont la seule documentation nécessaire pour le cours.

Livres

• Goodfellow, I., Bengio, Y., Courville, A. and Bengio, Y., 2016. Deep learning (Vol. 1, No. 2). Cambridge: MIT press.
• Nielsen, M.A., 2015. Neural networks and deep learning (Vol. 2018). San Francisco, CA: Determination press.
• Barber, D., 2012. Bayesian reasoning and machine learning. Cambridge University Press.
• Lay, D.C., 2003. Linear algebra and its applications.
• Stewart, J., 2009. Calculus: Concepts and contexts. Cengage Learning.

Articles

• Cybenko, G., 1989. Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems, 2(4), pp.303-314.
• Hornik, K., 1991. Approximation capabilities of multilayer feedforward networks. Neural networks, 4(2), pp.251-257.
• Telgarsky, M., 2015. Representation benefits of deep feedforward networks. arXiv preprint arXiv:1509.08101.
• Eldan, R. and Shamir, O., 2016, June. The power of depth for feedforward neural networks. In Conference on learning theory (pp. 907-940).
• Hanin, B., 2018. Which neural net architectures give rise to exploding and vanishing gradients?. In Advances in Neural Information Processing Systems (pp. 582-591).
• Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A. and Vandergheynst, P., 2017. Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine, 34(4), pp.18-42.
• Belkin, M. and Niyogi, P., 2003. Laplacian eigenmaps for dimensionality reduction and data representation. Neural computation, 15(6), pp.1373-1396.
• Kingma, D.P. and Welling, M., 2019. An introduction to variational autoencoders. arXiv preprint arXiv:1906.02691.
• Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B. and Bharath, A.A., 2018. Generative adversarial networks: An overview. IEEE Signal Processing Magazine, 35(1), pp.53-65.
• Morizet, N., 2020. Introduction to Generative Adversarial Networks (Doctoral dissertation, Advestis).
• Nickel, M. and Kiela, D., 2017. Poincaré embeddings for learning hierarchical representations. In Advances in neural information processing systems (pp. 6338-6347).
• Mathieu, E., Le Lan, C., Maddison, C.J., Tomioka, R. and Teh, Y.W., 2019. Continuous hierarchical representations with poincaré variational auto-encoders. In Advances in neural information processing systems (pp. 12565-12576).
• Goodfellow, I., 2016. NIPS 2016 tutorial: Generative adversarial networks. arXiv preprint arXiv:1701.00160.

Moodle: https://ena.etsmtl.ca/

Site web de l'enseignant: https://groyfortin.github.io