3.0.0

New in this release:

1. Updated to work with tensorflow 2.17
2. Improved display of activations in layers
3. SimpleNetwork is now SequentialNetwork
4. Refactored aitk.networks
5. Added tests

2.0.3

This version contains many fixes, especially in the notebooks.

Minor code updates:

1. Fix in robot speak()
2. New flowers and nanoGPT_shakespeare datasets

2.0.0

Moved all of the aitk modules together.

1.0.18

aitk: Artificial Intelligence Toolkit

This collection contains two things: an open source set of Python tools, and a set of computational essays for exploring Artificial Intelligence, Machine Learning, and Robotics. This is a collaborative effort started by the authors, building on almost a century of collective experience in education and research.

The code and essays are designed to require as few computing resources as necessary, while still allowing readers to experience first-hand the topics covered.

Authors

• Lisa Meeden - Professor in the Computer Science Department at Swarthmore College
• Jim Marshall - Professor in the Computer Science Department at Sarah Lawrence College
• Douglas Blank - Emeritus Professor of Computer Science, Bryn Mawr College; Head of Research at Comet.ml

1.0.16

Major changes:

aitk.robots:

• Allow distance to work with multi-dimensional points
• Return a copy with get_image() by default
• Fix off-by-one error in add_device_ring; allow device_class to be string

aitk.algorithms:

• Renamed properties of GA to snake_case
• added dependencies; add novelty; use snake_case
• Added GA.mutate_gene(gene)

1.0.2

Requires:

• "aitk.robots>=0.7.5"
• "aitk.networks>=0.2.5"
• "aitk.utils>=0.0.5"

1.0.1

Requires:

• "aitk.robots>=0.7.4"
• "aitk.networks>=0.2.4"
• "aitk.utils>=0.0.4"