Dive into Deep Learning
Interactive deep learning book with code, math, and discussions

Implemented with NumPy/MXNet, PyTorch, and TensorFlow

https://d2l.ai/index.html

🎉 release swyft 0.2.0, a practical machine learning tool for robust simulation-based inference in physics.
Python package: GitHub
🪄 Simulation-based inference can do magic. How can swyft help?

Read the thread.

🍀 Suggest name of a Python package for the
"Simulation of complex network dynamics with differential equations"
using just in time compilation (jitc).
It use phase and population models for simulation of interaction nodes.
netsim and pysim already taken.

Deep Learning, which is a course on the theory and techniques of deep learning with an emphasis on neuroscience. The course runs from August 2-20.
The syllabus for this course is still in progress, here is the current draft.

[ link ]

Follow: @theTuringMachine

Machine learning, computer vision, statistics and general scientific computing for .NET

https://github.com/accord-net/framework
#ML

A Student's Guide to Python for Physical Modeling: Second Edition
#python
#book
#beginner

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.

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

#book
#course
#ML