Not logged inCSS-Forum
Forum CSS-Online Help Search Login
CSS-Shop Impressum Datenschutz
Up Topic Hauptforen / Schachprogrammierung / TensorFlow Keras
- By Lothar Jung Date 2021-10-31 10:04 Edited 2021-10-31 10:15 Upvotes 1
Hier der Wikipedia Artikel:

https://de.wikipedia.org/wiki/TensorFlow?wprov=sfti1

Hier die Homepage:

https://www.tensorflow.org/overview?hl=de

Hier ein Schachprogramm auf GitHub:

https://github.com/crypt3lx2k/Zerofish

Hier der YouTube Kanal zu TensorFlow:

https://youtube.com/c/TensorFlow
- By Lothar Jung Date 2021-11-04 08:23 Upvotes 1
Ein Artikel, wie man seine eigene AlphaZero AI mit Python und Keras verwirklicht:

https://medium.com/applied-data-science/how-to-build-your-own-alphazero-ai-using-python-and-keras-7f664945c188
- By Lothar Jung Date 2022-10-10 14:11 Upvotes 1
The differences between wide and deep approaches on different problems are quite interesting. on recommender systems, wide architecture was linked more to **memorization** while deep architecture was linked more to **generalization** (https://ai.googleblog.com/2016/06/wide-deep-learning-better-together-with.html).
On image classification, wide architecture was shown to be significantly better at classifying imagenet classes related to **"structure", "scenes", or "geological formation"** while deep architecture was significantly better on image classes related to **"consumer goods"**, others not much significant difference (https://ai.googleblog.com/2021/05/do-wide-and-deep-networks-learn-same.html). It would  be interesting how these translate to leela architecture or just chess in general. the terms "memorization", "generalization", and "structure" also have analogues in learning chess, so it kinda begs a hypothesis on how the wide vs deep architecture difference would manifest in leela.

http://ai.googleblog.com/2016/06/wide-deep-learning-better-together-with.html
- By Lothar Jung Date 2023-07-18 09:58
https://keras.io/keras_core/announcement/

We're excited to share with you a new library called Keras Core, a preview version of the future of Keras. In Fall 2023, this library will become Keras 3.0. Keras Core is a full rewrite of the Keras codebase that rebases it on top of a modular backend architecture. It makes it possible to run Keras workflows on top of arbitrary frameworks — starting with TensorFlow, JAX, and PyTorch.
Up Topic Hauptforen / Schachprogrammierung / TensorFlow Keras

Powered by mwForum 2.29.3 © 1999-2014 Markus Wichitill