We cannot cope with randomnessRandomness is liberating, yet our thinking keeps rejecting it. From games of chance to victim-blaming and self-help books, our thinking…Oct 24, 20221Oct 24, 20221
Reversing the Chinese Room: brains are computers, and all computers can feel and thinkFar from supporting Searle’s conclusion, the Chinese Room is actually a very good argument for emergent qualities in physical systems like…May 18, 2022May 18, 2022
We cannot know if we have free will, and so maybe all science is brokenWe cannot decide whether humans have free will because we experience time as monotonic. This fact, surprisingly, also undermines the…May 15, 2022May 15, 2022
Published inTowards Data ScienceLinear and Logistic Regressions as Degenerate Neural Networks in KerasNeural networks are supersets of linear and logistic regressions. Use Keras to quickly and efficiently build regression models.Apr 17, 2022Apr 17, 2022
The Best DefenseIt all started when Base II (there had been no contact with Base I for some years by then), so when Base II decided that we should go and…Jan 5, 2022Jan 5, 2022
How to write (or customise) a templating engine?While working on extending a web templating system to support a new programming language, I collected some features I wanted to implement…Nov 27, 2020Nov 27, 2020
Published inTowards Data ScienceInterpreting Neural Networks by Reducing Nonlinearities during TrainingThis note describes a method of reducing the complexity of a neural network during its training and extracting human-readable rules from…Jun 28, 2020Jun 28, 2020
Published inManagement MattersRemote Management in 9 Simple Steps: A Quick Practical Guide to Transitioning Away from the OfficeThis note offers practical ideas to team leaders and managers who suddenly find themselves managing their team remotely.Jun 27, 2020Jun 27, 2020
