Finding the coarser description that keeps what matters — in learning, in voting, in harmony, in the brain. I suspect these are all the same question and I cannot yet say why.

Chords are shapes July 20, 2026
What an isomorphic keyboard makes visible about harmony

The Geometry of Governance January 3, 2026
Voting as a compression problem, and the right to be heard

Ikram and his tricks October 8, 2025
A Tale of Clay and Calculation

Intelligent Immunity May 27, 2025
What if intelligence evolved within the immune system?

Every Bias Names an Algorithm March 25, 2025
Bounded reasoners trade accuracy for efficiency in three places, and each trade leaves its own fingerprint

Graph enumeration January 10, 2024
The orderly enumeration of graphs

The fable of the caterpillar February 25, 2019
A fun intro to my masters topic; abstraction for efficient reinforcment learning.

The advantages of backward reasoning. October 20, 2018
A simple exploration of what can be gained by reasoning backwards from your goal.

Automated science August 22, 2018
Model-based reinforcement learning, symbolic AI, and the limits of efficient learning.

Principles of neural design August 13, 2018
Note from reading the book.

Unsupervised skip connections May 30, 2018
How can we use ladder nets in the unsupervised setting?

Visualising dataset alignment February 10, 2018
Dataset alignment represented as tensor networks

Conserved complexity September 26, 2017
A conservation law for algorithms?

Saddles, Splitting, and Reparameterization September 26, 2016
Dynamically Growing Neural Networks

A functional type of non-linear algebra? September 26, 2016
Functional programming plus neural network architectures.

Representations within linear algebra September 26, 2016
We can use linear algebra to represent; linear operators, algebras, computations, symmetry and more.