What we're about
This group is set up for learning and discussing anything related to an intersection of Philosophy and Computer Science.
We aim to engage participants in a group conversation to explore a wide range of topics including Complexity Theory, Systems Thinking, Computability, Emergence, Physics, Analytical Philosophy, Economy ...and the rest is just engineering what means we are also interested in searching the space of open-source projects, models and computational experiments.
The group is inspired by activity of Santa Fe Institute but is not an official SFI event.
List of topics discussed so far with links to presentations:
• Information as a physical entity, entropy and life - With Radosław A. Kycia. Landauer's principle, Galois connections and bits of Category Theory. Also some inspiration from Paul Davies "The Demon in the Machine"
• Zero-knowledge proofs - With Ariel Gabizon. Examples, from interactive to non-interactive, elliptic curves, homomorphic encryption, Zero-knowledge contingent payment.
• Natural born algorithms - Digital Philosophy. Turing complete cellular automatons. Seth Lloyd's Universe as a computer.
• Computing Chaitin's Omega - Algorithmic Information Theory vs principle of sufficient reason
• Limits of AI. The Gödelian argument - Incompleteness theorems, Penrose's examples, Aaronson's classification
• Randomness from determinism - cellular automaton, S. Wolfram's rule 30, pseudo randomness
• Inspiration for the group - inspiration, audience, format, rules, possible topics
Upcoming events (1)
After a break let’s meet, discuss and learn from Lukasz Dębowski about language models and power laws.
“Large language models based on transformers and trained on nearly internet-sized corpora of text, such as OpenAI's chatGPT, are revolutionizing natural language processing and revive the dream of artificial general intelligence. They have made huge progress within a few years, leaving us largely intellectually unprepared for their arrival. In my talk, I will attack the topic of language models from a mathematician's perspective. I will speak of empirical power laws of learning in these models and I will present a simplistic model of language and learning that exhibits such laws” - Łukasz Dębowski, Instytut Podstaw Informatyki PAN.
Lukasz Dębowski, PhD https://home.ipipan.waw.pl/l.debowski/ focuses on information theory, complex systems, discrete stochastic processes and goes further into statistical and neural language models. His latest book "Information Theory Meets Power Laws: Stochastic Processes and Language Models" received the prize of the Committee on Informatics of the Polish Academy of Sciences.
For a warm and entertaining introduction to power laws, try Michael Stevens’, Vsauce: The Zipf Mystery
Agenda: Discuss, watch videos, plan the next meetings.
Goal: learn, discuss & have fun
- Ernest S.
- Andre P.
- Marcin S.
- 18 attendees
Past events (6)
- Marcin S.
- Adam S.
- Adam W.
- 30 attendees
