Complete file set for Jupyter Book
Autor: Wojciech Broniowski
Date: 17 July 2021
ISBN: 978-83-962099-0-0 (pdf version)
These undergraduate lectures explain the very basic concepts of neural networks at a most elementary level, requiring only very rudimentary knowledge of Python, or actually any programming language. With simplicity in mind, the codes for various algorithms are written from absolute scratch, i.e. without any use of dedicated higher-level libraries. That way one can follow all the programming steps in an explicit manner.
The book is intended for undergraduate students and for advanced high school pupils and their teachers.
How to run the executable book codes:
A major advantage of executable books is that the reader may enjoy running the source codes himself, modifying them and playing around. No downloading, installation or configuration are required. Simply go to
https://bronwojtek.github.io/neuralnets-in-raw-python/docs/index.html,
in the left menu select any chapter below the Introduction, click the "rocket" icon at the top right of the screen, and choose (preferably) "Colab" or “Binder" (which can be slow). After some initialization time the notebook can be run.
Links:
-
Jupyter Book: https://bronwojtek.github.io/neuralnets-in-raw-python/docs/index.html
-
pdf: file nn_book_covers.pdf (131 pages)
-
codes: www.ifj.edu.pl/~broniows/nn or www.ujk.edu.pl/~broniows/nn