This post illustrates why surprise is an intuitively useful quantity.
A segway into information theory
Information theory may be useful for understanding active inference. As a minimum it offers some alternative perspectives on the quantities used in the active inference theory such as surprise, KL divergence, and entropy. This post provides a very short introduction to information theory.
A deeper look at perceptual inference
In this post we will take a deeper look at how, according to the active inference theory, the brain interprets what it observes.
Active inference lecture notes
I have set out to gain some insights into the active inference theory that provides a unified framework for perception, learning, decision making, and action. I will share my “lecture notes” combined with my own comments in this and future posts. My focus is on the mathematical models and the necessary algorithms.
Is artificial intelligence a threat to humanity?
I’m worried about irreversible climate change, nuclear war, war on rationality, isolationism, extreme nationalism, intolerance, pandemics, the declining mental health of the young, religious extremism, bioterrorism, and many other things. AI doesn’t make it to my top 10 list. Why?
Under resurrection…
This blog has been dormant for a few years because of other priorities. Now I again feel the urge to write as a tool for learning and because some recent developments in the world just need to be commented.
No limits
Everything that is not forbidden by the laws of nature is achievable, given then right knowledge.
A saying
A piece of old but current wisdom from Hávamál.
The future is electric
Today I make a new prediction: the future of transportation is electric.
Scrap the Safe Drinking Water Act!
Who cares about clean air and safe drinking water anyway?