Despite continuing to work in the Internet space, my principal means of analysis exploits findings in biotechnology and quantitative ecology. In addition to random projections, I'm studying applications of shrinkage and the LASSO for document-term matrices and regression based upon them.
Doing a bit of stuff with random projections from high dimensional space to two dimensions, these days. Both simple projections, like those described at https://667-per-cm.net/2018/11/20/the-johnson-lindenstrauss-lemma-and-the-paradoxical-power-of-random-linear-operators-part-1/ and much more sophisticated presentations, like those studied and engineered by M. C. Thrun and colleague A. Ultsch, per https://www.researchgate.net/profile/Michael_Thrun/publication/326413234_Investigating_Quality_Measures_of_Projections_for_the_Evaluation_of_Distance_and_Density-based_Structures_of_High-Dimensional_Data/links/5b4c2f0845851519b4c02a63/Investigating-Quality-Measures-of-Projections-for-the-Evaluation-of-Distance-and-Density-based-Structures-of-High-Dimensional-Data.pdf
Grad student pursuing a PhD in mathematics. Outside of math, I'm interested in cognitive science, ecology, permaculture, and political theory.
Interested in Conceptual Space Theory, NLP, analogy & metaphor, and cognitive/developmental robotics. Perhaps Category Theory can help me become a better AI engineer?
Hi Robert,
I have been looking at RedPRL quite a bit, and am very interesting in learning more about it. I was wondering if you had thought of domains or applications wherein the language might be useful, but is not currently be used. For example, if I were working to apply Category theory to some areas of biology, do you think the language would be particularly suited to computational models of this area? I guess I am wondering if there are things that can be expressed elegantly in the language, that are maybe not being done currently. Do you have any thoughts? I apologize if this may be too speculative of a question, but I am genuinely curious. Thank you.
Best, Grant
Computer science Master student at the University of Zagreb, Croatia. I'm interested in understanding how intelligence works in the most universal way possible - which seems to be the language of category theory. I have plenty of experience with deep neural networks (see my github ) and now I'm attending the ACT course and getting solid foundations in CT.
I'm happy to talk about anything related to CT or machine learning - feel free to drop me a message!
Mathematician (with master thesis about Atiyah-Hirzebruch-sequences and Postinkov systems). Since then worked within IT projects for 20 years. Last 10 years as teacher at Universities for applied sciences mainly on economics mathematics. Now retired. Interested in System Dynamics, simulation and Causal Loop Diagrams (CLD) and Archetypes. I'm trying to understand CLD in a categorial manner.
I’m interested in expanding the intersection of functional programming and machine learning.
Hello - I studied Measure Theory, Stochastic Calculus and Information Theory 1985-1988 and mainly worked in financial risk management of derivatives businesses. I came across OCaml and heard about 'abstract nonsense' in about 2006 but didn't study it and am still often lost in terminology. However, Bartosz Milewski series of videos has been extremely helpful to get going. I appreciate John Baez's evangelism and his ability to link ideas from physics and other domains with interesting maths. Mike Stay's early posts demonstrating many concepts in Javascript (rather than Haskell) were also accessible. I'm interested in the Categorical point-of-view applied to convex optimisation (dual problems), time-series databases (immutable streams) and image processing (convolutional operators).
Changing the units is an isometry so it's pretty straight forward.