~~stoggle_buttons~~
====== Machine Learning & Physics ======
   * [[https://towardsdatascience.com/physics-guided-neural-networks-pgnns-8fe9dbad9414| Physics guided neural networks]] -> La función de coste tendrá el término de regularización para evitar overfitting, pero también un término de "sentido físico" que penalice soluciones que no tienen sentido físico
   * [[http://theorangeduck.com/page/machine-learning-kolmogorov-complexity-squishy-bunnies|Machine Learning, Kolmogorov Complexity, and Squishy Bunnies]] NN para interpolar funciones no lineales (en este caso implementar un modelo de físicas con NN, imagino que algo parecido a "linealizarlo" para que pueda correr en una GPU). También las NN parecen funcionar muy bien en [[https://arxiv.org/abs/1910.07291|Solving the three-body problem using DNNs]]
   * [[https://arxiv.org/abs/1912.12132|Machine Learning for Precipitation Nowcasting from Radar Images]] Predicción de tiempo basándose en patrones de imágenes de radar. Dicen que es más preciso a corto tiempo y localmente que simulaciones de modelos físicos
   * [[https://m.phys.org/news/2020-01-physics-analog-recurrent-neural-network.html|Wave physics as an analog recurrent neural network]]
   * [[https://towardsdatascience.com/understanding-variational-autoencoders-vaes-f70510919f73|Understanding Variational Autoencoders (VAEs)]]
   * [[https://arxiv.org/abs/1912.05634|Self-regularizing restricted Boltzmann machines]]
   * [[https://towardsdatascience.com/variational-inference-ising-model-6820d3d13f6a|Variational Inference: Ising Model]] Maximizar la divergencia KL para quitarle el ruido a una imagen
   * [[https://www.cs.ubc.ca/~murphyk/MLbook/pml-toc-22may12.pdf|Machine Learning: A Probabilistic Perspective]] Libro muy muy completo, tiene de todo, desde estadística hasta ML avanzado.
   * [[https://web.stanford.edu/~hastie/ElemStatLearn/printings/ESLII_print12.pdf|The Elements of Statistical Learning]] También avanzado, muy conocido
   * [[https://www.oreilly.com/radar/why-you-should-care-about-debugging-machine-learning-models/|ML Debugging]]
   * [[https://dafriedman97.github.io/mlbook/content/introduction.html|mlbook]] This book is for readers looking to learn new machine learning algorithms or understand algorithms at a deeper level, for readers interested in seeing machine learning algorithms derived from start to finish
   * [[https://distill.pub/]] Interesting blog about advanced ML/Physics
   * [[https://github.com/lab-ml/nn|LabML Neural Networks]] A collection of implementations of neural network architectures and related algorithms  kept simple and easy to read
   * [[https://medium.com/ontologik/are-nns-just-fuzzy-hashtables-a-revealing-experiment-on-mnist-data-d5b0c773bf40|Are Neural Networks just Fuzzy Hashtables?]] Experiments using MINST dataset
   * [[https://arxiv.org/abs/1602.02830|Binarized Neural Networks (Weights and Activations to +1 or -1)]]
   * [[https://physicsml.github.io|〈 physics | machine learning 〉]]
===== Renormalization group & Neural networks =====
  * [[https://towardsdatascience.com/deep-learning-explainability-hints-from-physics-2f316dc07727|Resumen 
de Marco Tavora]] Alto nivel, se mete con algo de matemáticas pero no demasiado
   * [[https://dspace.library.uu.nl/handle/1874/366784|Renormalization Group connected to Neural Networks]] La mejor review del tema que he encontrado hasta el momento. Modelizar las NN como redes de spines (Ising, Boltzmann Machines...), las matemáticas son las mismas y hay muchas analogías.


===== Generative Adversarial Networks (GANs) =====
   * [[https://medium.com/mlreview/the-intuition-behind-adversarial-attacks-on-neural-networks-71fdd427a33b| The intuition behind adversarial attacks on NN]] -> Las imágenes adversarias podrían estar creadas por la función de activación de las neuronas (x*(x>0) en vez de más robustas como tanh(x) o sigm(x)) que se sobreexcita al no estar acotada por arriba.
   * [[https://towardsdatascience.com/understanding-generative-adversarial-networks-gans-cd6e4651a29|Understanding Generative Adversarial Networks (GANs)]]
   * [[https://towardsdatascience.com/must-read-papers-on-gans-b665bbae3317|Must-Read Papers on GANs]]
   * [[https://towardsdatascience.com/comprehensive-introduction-to-turing-learning-and-gans-part-1-81f6d02e644d|Turing Learning and GANs Part 1]]
   * [[https://towardsdatascience.com/comprehensive-introduction-to-turing-learning-and-gans-part-2-fd8e4a70775?_branch_match_id=735924017099318752&gi=9ff345c907aa|Turing Learning and GANs Part 2]]
   * [[https://link.medium.com/wd4TYSUV12|GAN Visualization]]
   * [[https://arxiv.org/abs/1907.07174|Natural Adversarial Examples]]
   * [[http://bactra.org/weblog/2014-11-13-intriguing-properties.html]] Redes adversarias en profundidad
   * [[https://www.theverge.com/2020/8/4/21353810/facial-recognition-block-ai-selfie-cloaking-fawkes|Fawkes]] poner ruido encima de una imagen: imperceptible para humanos, las redes no dan una (no sé si es GAN realmente)
   * [[https://machinelearningmastery.com/what-are-generative-adversarial-networks-gans/|A Gentle Introduction to GANs]]
   * [[https://machinelearningmastery.com/]]
   * [[https://arxiv.org/abs/1712.09665|Adversarial Patch]]
     * We present a method to create adversarial image patches in the real world.
       * universal (can be used to attack any scene)
       * robust (work under a wide variety of transformations)
       * targeted (cause a classifier to output any target class) 

===== ML & Control =====
   * [[http://www.argmin.net/2018/06/25/outsider-rl/|Reinforcement Learning y Control de Sistemas]]
   * [[https://github.com/tensorboy/PIDOptimizer/blob/master/README.md|PID para Stochastic Descent Gradient]]
===== ML & Quantum Physics =====
Son una ida de olla?
  * [[https://arxiv.org/abs/1910.13804|Quantum Optical Experiments Modeled by Long Short-Term Memory]]

===== Recursos generales =====
  * [[https://distill.pub/]]
  * [[https://paperswithcode.com/]]