mastodon 4.7.2ASU Associate Prof in SCAI/SOLS. Interdisciplinary research in autonomous decision making in living and artificial systems. Director of the Bringing Ecology and Engineering Together (BEET) Lab at Arizona State University.
Research interests: behavioral ecology, OFT, social insects, multi-agent systems/robotics, automation in the built environment, animal behavior, ethics in autonomy, AI/ML
https://bsky.app/profile/tedpavlic.bsky.social
https://x.com/TedPavlic
TEDx: http://youtu.be/9GWXCRetOjk
Reservoir Computing is traditionally a difficult topic for students -- using an untrained recurrent neural network as a feature extractor for time-series analysis. I put together this widget to highlight how these tools turn temporal into spatial patterns.
https://tpavlic.github.io/asu-bioinspired-ai-and-optimization/reservoir_computing/esn_explorer.html
After getting some questions from students about MLP architectural choices and how backpropagation works, I put together this comprehensive multi-layer perceptron/backpropagation explorer (with a lot of cool latent-space visualizations, some in 3D!):
https://tpavlic.github.io/asu-bioinspired-ai-and-optimization/multi_layer_perceptron/mlp_explorer.html
