Active Inference Insights Sanjeev Namjoshi ~ Active Inference Insights 018 ~ Education, Expectation-Maximisation, Evolution
14 snips
Jun 17, 2024 Join Sanjeev Namjoshi, a textbook-writing, Bayesian-educating enthusiast, in a discussion covering the teaching of active inference, its relation to evolution, and learning mechanisms. Explore topics like unsupervised learning, Bayesian inference, survival strategies in a dynamic world, expectation maximization, simplifying mathematics for active inference, using Python, R, and MATLAB for simulations, the influence of priors in Bayesian modeling, mathematical concepts in active inference, phenotypic priors in AI, and cutting-edge topics on intelligence and gratitude.
AI Snips
Chapters
Transcript
Episode notes
Unusual Path To Active Inference
- Sanjeev discovered active inference after a diversified academic path across neurobiology, genetics, biochemistry and bioinformatics.
- He stumbled on Karl Friston's papers around 2018 and realised his interests converged into active inference.
Prerequisites And How To Learn Active Inference
- Learn probability theory first, then single-variable calculus, then linear algebra as needed.
- Practice with simple Python simulations to build intuition before tackling full multivariate models.
Probability Theory Is The Core
- Active inference can be reduced to probabilistic (Bayesian) reasoning at its core.
- Probability theory provides a common language to translate neuroscience and bioinformatics methods into active inference.