playlist con le sessioni registrate: https://www.youtube.com/playlist?list=PL4fOYM4iG6elOwDkG_SdkIpPphe2wBCWI
Esercizi svolti in Python: https://github.com/empathy87/The-Elements-of-Statistical-Learning-Python-Notebooks/blob/master/examples/South%20African%20Heart%20Disease.ipynb
🖌️ CycleGAN:
Paper CycleGAN: https://arxiv.org/abs/1703.10593
Un’implementazione in Pytorch: https://github.com/yunjey/mnist-svhn-transfer
🐶 Reinforcement Learning:
Tutorial sul reinforcement learning di Pytorch: https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html
Sutton, Barto “Reinforcement Learning: An Introduction”: http://incompleteideas.net/book/the-book.html
🕸️ GNN:
DeepMind “Learning to Simulate Complex Physics with Graph Networks”, https://arxiv.org/pdf/2002.09405.pdf
Video introduzione GNN: https://www.youtube.com/watch?v=fOctJB4kVlM&t=343s
Introduzione “visiva” alle GNN: https://distill.pub/2021/gnn-intro/
Spettro degli autovalori di un grafo: 1) http://blog.shriphani.com/2015/04/06/the-smallest-eigenvalues-of-a-graph-laplacian/
2) https://www.frontiersin.org/articles/10.3389/fncom.2013.00189/full
3) https://towardsdatascience.com/spectral-graph-convolution-explained-and-implemented-step-by-step-2e495b57f801
Google, “Attention is all you need” : https://arxiv.org/pdf/1706.03762.pdf
Un’ottima e sintetica spiegazione dei transformer: https://jalammar.github.io/illustrated-transformer/
Una spiegazion un po’ più lunga: Transformers Explained Visually.
Part 1: https://towardsdatascience.com/transformers-explained-visually-part-2-how-it-works-step-by-step-b49fa4a64f34
Part 2: https://towardsdatascience.com/transformers-explained-visually-part-1-overview-of-functionality-95a6dd460452
📥 Word embedding:
https://jalammar.github.io/illustrated-word2vec/
🧠 Pytorch, machine learning e neural networks:
Come funziona Pytorch Autograd?: https://www.youtube.com/watch?app=desktop&v=MswxJw-8PvE
Andrew NG, “Machine Learning Yearning”, https://github.com/ajaymache/machine-learning-yearning
“Dive into Deep Learning”: https://d2l.ai/index.html