Chaos Everywhere - Part 2!
Chaos + Noise = Neurochaos Learning!
That's not a metaphor. It's a working equation, and it powers a new paradigm of brain-inspired machine learning called Neurochaos Learning (NL).
In our first session, Dr Nithin Nagaraj took us through the beautiful, strange world of Chaos Theory hiding inside simple 1D maps. This time, we go deeper into what happens when you leverage chaos for machine learning.
Dr Nithin will be discussing how chaotic neural architectures classify SARS-CoV-2 viral genome sequences, outperforming conventional ML models on a problem that mattered during COVID. What happens when you deliberately inject noise into a chaotic learning system (spoiler: it gets better, stochastic resonance in Neurochaos Learning)
He will also show how chaotic transformations preserve causal structure in data, a result presented at NeurIPS 2022
Part 1 of the talk here with speaker details: https://luma.com/qvgbk6j4
Speaker:
Dr Nithin Nagaraj is Professor and Head of the Complex Systems Programme at the National Institute of Advanced Studies (NIAS), Bengaluru, and a member of its Consciousness Studies Programme.
LinkedIn: https://www.linkedin.com/in/nithin-nagaraj-14b07934
To attend online:
Add to calendar: https://shorturl.at/zguXK
Gmeet link: meet.google.com/ace-jthv-apo
Pre-read:
Harikrishnan NB et al., "Classification of SARS-CoV-2 viral genome sequences using Neurochaos Learning", Medical & Biological Engineering & Computing, 2022. Read here
Harikrishnan NB, Nithin Nagaraj, "When Noise meets Chaos: Stochastic resonance in Neurochaos Learning", Neural Networks, 2021. Read here
Harikrishnan NB et al., "Causality Preserving Chaotic Transformation and Classification using Neurochaos Learning", NeurIPS 2022. Read here
Looking forward to seeing you!