Still I recommend these books. 👌🤌

Jupyter Book

Jupyter Book is an open-source project for building books and documents from standard computational and data science materials such as Jupyter Notebooks and Markdown documents.


Official documentation
https://jupyterbook.org/

JITCSIM
I have written a package for high performance simulation of complex networks using just in time compilation.
The model is written in python syntax, C code is generated and run with full speed.

This is not an official release, I have made the project public to get some feedback, and know how much this could be helpful for others.

It includes the Kuramoto models and solve ODEs and SDEs.

Delay differential equations will be added soon.

Parallelising with OpenMP and Multiprocessing also supported.

To get a glance what is now available look at the notebooks.

Delay differential equations have numerous applications in science and engineering. This short, expository book offers a stimulating collection of examples of delay differential equations which are in use as models for a variety of phenomena in the life sciences, physics and technology, chemistry and economics. Avoiding mathematical proofs but offering more than one hundred illustrations, this book illustrates how bifurcation and asymptotic techniques can systematically be used to extract analytical information of physical interest.

Applied Delay Differential Equations is a friendly introduction to the fast-growing field of time-delay differential equations. Written to a multi-disciplinary audience, it sets each area of science in his historical context and then guides the reader towards questions of current interest.

#book
#DDE

Introduction to Deep Learning

-- 170 Video Lectures from Adaptive Linear Neurons to Zero-shot Classification with Transformers
Jul 9, 2021
by Sebastian Raschka

#course
#DL

This the first release of JiTCSim.

The followings are available:

- Kuramoto model simulation on arbibtrary networks.
- Using control parameter to avoid multiple compilation.
- Solving ODE/DDE/SDE system of equation using JiTC*DE packages.
- Parallel simulation using multiprocessing and OpenMP
- Calculation of the Hysteresis loop for explosive synchronization
- Calculation of Lyapunov exponents spectrum.
- Please let me know your comments.

https://github.com/Ziaeemehr/JITCSIM

HTML documentation page is UP:
https://ziaeemehr.github.io/JITCSIM/

I have made some interactive dashboard for brian.
Let's take a look.

GitHub

Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control
Steven L. Brunton, J. Nathan Kutz

Data-driven discovery is revolutionizing the modeling, prediction, and control of complex systems. This textbook brings together machine learning, engineering mathematics, and mathematical physics to integrate modeling and control of dynamical systems with modern methods in data science. It highlights many of the recent advances in scientific computing that enable data-driven methods to be applied to a diverse range of complex systems, such as turbulence, the brain, climate, epidemiology, finance, robotics, and autonomy. Aimed at advanced undergraduate and beginning graduate students in the engineering and physical sciences, the text presents a range of topics and methods from introductory to state of the art.

http://databookuw.com/
Matlab and Python codes available.
Video lectures by authors available on YouTube.

#book
#course
#ML

Montbrio Dashboard

Montbrió, E., Pazó, D. and Roxin, A., 2015. Macroscopic description for networks of spiking neurons. Physical Review X, 5(2), p.021028.

GitHub

t.me/scientific_programming

JAX is NumPy on the CPU, GPU, and TPU, with great automatic differentiation for high-performance machine learning research.

With its updated version of Autograd, JAX can automatically differentiate native Python and NumPy code. It can differentiate through a large subset of Python’s features, including loops, ifs, recursion, and closures, and it can even take derivatives of derivatives of derivatives. It supports reverse-mode as well as forward-mode differentiation, and the two can be composed arbitrarily to any order.

Link

بازسازی کیفیت تصاویر قدیمی با یادگیری عمیق!

معماری GFP-GAN یک مدل هوش مصنوعی رایگان برای ترمیم عکس است.

GFPGAN aims at developing Practical Algorithm for Real-world Face Restoration.
It leverages rich and diverse priors encapsulated in a pretrained face GAN (e.g., StyleGAN2) for blind face restoration.

GitHub

Implemented in #jitcsim

GitHub

Kachhvah, A.D. and Jalan, S., 2017. Multiplexing induced explosive synchronization in Kuramoto oscillators with inertia. EPL (Europhysics Letters), 119(6), p.60005.

Check out this learning material called Statistics and Machine Learning in Python.

The book contains :
- Python ecosystem for data science
- Python and scientific python
- Statistics in Python
- ML in python
- Deep Learning

Credit : Authors (Edouard Duchesnay, Tommy Löfstedt, Feki Younes)

#ML
#book

Case Studies in Neural Data Analysis
Author: Mark Kramer and Uri Eden

This repository is a companion to the textbook Case Studies in Neural Data Analysis, by Mark Kramer and Uri Eden. That textbook uses MATLAB to analyze examples of neuronal data. The material here is similar, except that we use Python.

[ link ] [ git ] [ book ]

Follow: @theTuringMachine