Instructions to use ericyoc/the_applied_ai_universe_coding_guide with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use ericyoc/the_applied_ai_universe_coding_guide with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://ericyoc/the_applied_ai_universe_coding_guide") - Notebooks
- Google Colab
- Kaggle
metadata
license: mit
library_name: keras
datasets:
- ylecun/mnist
- uoft-cs/cifar10
tags:
- adversarial-ml
- security
- adversarial-robustness
- adaptive-ai-codex
The Applied AI Universe Coding Guide
Trained models and figures from Book 1 - the clean baselines that Books 2 and 3 attack and defend. Includes scikit-learn classifiers (.skops), Keras networks (.keras, loadable standalone), quantum circuit parameters (.npz), symbolic state (.json), and every figure the book generates.
The Adaptive AI Codex Series
Book 1 by Eric Yocam, PhD, DBA.
| Title | Links | |
|---|---|---|
| 1 | The Applied AI Universe Coding Guide | Amazon 路 Site 路 GitHub |
| 2 | ...: Adversarial Attacks | Amazon 路 Site 路 GitHub |
| 3 | ...: Adversarial Defenses | Coming 2026 路 Site 路 GitHub |
Series overview: https://ericyocam.com/applied-ai-universe-coding-guide.html