Con l'avvento e l'uso comune di sistemi di "intelligenza artificiale" (chatGPT, google LENS, …) anche i non addetti ai lavori si trovano esposti ai sistemi di RETI NEURALI. Questo tipo di algoritmo, infatti, è alla base di tutti i più famosi sitemi di AI.
Nel video di oggi vedremo la teoria alla base delle Deep Neural Network, ma anche un nuovo approccio ideato di recente (maggio 2024) che sembra poter essere un nuovo protagonista dei sistemi AI, le reti di Kolmogorov-Arnold
Lasciate il like ed iscrivetevi!
✏️ Seguimi sui Socials ✏️
instagram: _mathita
twitch: www.twitch.tv/mathita_/
telegram: t.me/mathita_official
tutti i social: linktr.ee/mathita_
✏️ Links e Fonti ✏️
* [AL] drive.google.com/file/d/1bFZpHBPr5l-cd-m2XBqQuLeRzQvfIGdW/view
* [Cybenko 1989] CYBENKO, George. Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems, 1989, 2.4: 303-314.
link.springer.com/article/10.1007/BF02551274
* [Csaji et al. 2001] CSÁJI, Balázs Csanád, et al. Approximation with artificial neural networks. Faculty of Sciences, Etvs Lornd University, Hungary, 2001, 24.48: 7.
www.researchgate.net/profile/Balazs-Csaji/publication/357888472_Approximation_with_Artificial_Neural_Networks/links/61e5b56c5779d35951b55282/Approximation-with-Artificial-Neural-Networks.pdf
* [Liu et al. 2024] LIU, Ziming, et al. Kan: Kolmogorov-arnold networks. arXiv preprint arXiv:2404.19756, 2024.
arxiv.org/pdf/2404.19756
* [Yadav et al. 2015] YADAV, Neha, et al. An introduction to neural network methods for differential equations. Berlin: Springer, 2015.
link.springer.com/chapter/10.1007/978-94-017-9816-7_2
* [Raschka 2015] RASCHKA, Sebastian. Python machine learning. Packt publishing ltd, 2015.
* [Bishop 2006] BISHOP, Christopher M.; NASRABADI, Nasser M. Pattern recognition and machine learning. New York: springer, 2006.
link.springer.com/book/10.1007/978-0-387-45528-0
* [Goodfellow et al. 2016] GOODFELLOW, Ian; BENGIO, Yoshua; COURVILLE, Aaron. Deep learning. MIT press, 2016.
* [Heiberger et al. 2009] HEIBERGER, Richard M., et al. Polynomial regression. R Through Excel: A Spreadsheet Interface for Statistics, Data Analysis, and Grapsics, 2009, 269-284.
link.springer.com/chapter/10.1007/978-1-4419-0052-4_11
* [Peterson 2009] PETERSON, Leif E. K-nearest neighbor. Scholarpedia, 2009, 4.2: 1883.
scholarpedia.org/article/K-nearest_neighbor
* [Kramer et al. 2013] KRAMER, Oliver; KRAMER, Oliver. K-nearest neighbors. Dimensionality reduction with unsupervised nearest neighbors, 2013, 13-23.
link.springer.com/chapter/10.1007/978-3-642-38652-7_2
* [Pisner et al. 2020] PISNER, Derek A.; SCHNYER, David M. Support vector machine. In: Machine learning. Academic Press, 2020. p. 101-121.
www.sciencedirect.com/science/article/abs/pii/B9780128157398000067
* [Ginesi, Fiorini 2023] GINESI, Michele; FIORINI, Paolo. Generalization of Auto-Regressive Hidden Markov Models to Non-Linear Dynamics and Unit Quaternion Observation Space. IEEE Robotics and Automation Letters, 2023.
ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10202181
* [Yuanzhi et al. 2017] LI, Yuanzhi; YUAN, Yang. Convergence analysis of two-layer neural networks with relu activation. Advances in neural information processing systems, 2017, 30.
proceedings.neurips.cc/paper_files/paper/2017/file/a96b65a721e561e1e3de768ac819ffbb-Paper.pdf
* [Juncai et al. 2018] HE, Juncai, et al. ReLU deep neural networks and linear finite elements. arXiv preprint arXiv:1807.03973, 2018.
arxiv.org/pdf/1807.03973
* [Gu et al. 2018] GU, Jiuxiang, et al. Recent advances in convolutional neural networks. Pattern recognition, 2018, 77: 354-377.
www.sciencedirect.com/science/article/pii/S0031320317304120
* [Li et al. 2021] LI, Zewen, et al. A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems, 2021, 33.12: 6999-7019.
ieeexplore.ieee.org/abstract/document/9451544
* [Blalock et al. 2020] BLALOCK, Davis, et al. What is the state of neural network pruning?. Proceedings of machine learning and systems, 2020, 2: 129-146.
proceedings.mlsys.org/paper_files/paper/2020/file/6c44dc73014d66ba49b28d483a8f8b0d-Paper.pdf
* [Schmidt-Hieber 2021] SCHMIDT-HIEBER, Johannes. The Kolmogorov-Arnold representation theorem revisited. Neural networks, 2021, 137: 119-126.
www.sciencedirect.com/science/article/pii/S0893608021000289
✏️ Parti ✏️
00:00 - Introduzione
01:01 - cos'è il Machine Learning
02:37 - le Reti Neurali
11:10 - le Reti di Kolmogorov-Arnold
17:22 - Conclusione
✏️ Audio e Video ✏️
MOTORE GRAFICO: Manim → github.com/ManimCommunity/manim
MONTAGGIO: DaVinci Resolve → www.blackmagicdesign.com/products/davinciresolve/
MUSICHE: Libreria di UA-cam
#AI #matematica #neuralnetworks