# Mishka's Page

## Professional interests

Mathematics; Computer Science; Software Engineering;
Artificial Intelligence; Neural and Cognitive Science.

My resume.

I am trying to combine theoretical research and practical applications.

My theoretical interests concentrate in **applications of continuous
mathematics to computing** -
*domains for denotational semantics* give
the prime example of such applications. Another important area
of such applications is
realistic
neural networks.

My practical interests are in programming language design and
implementation, in methods and tools for software engineering,
and in audio-visual computer-based cognitive tools.

By the end of 2015, a degree of convergence between my theoretical
interests and my practical interests have emerged.
We finally have a model of computation
which allows us to *continuously deform programs* and, moreover,
to *represent large classes of programs by matrices of
real numbers.*

It turns out that the resulting **dataflow matrix machines** are
a fairly powerful generalization of **recurrent neural networks**.
A one-page overview of dataflow matrix machines (November 25, 2016).

The reference paper on this subject is currently
Dataflow
Matrix Machines and V-values: a Bridge between Programs and Neural Nets
(December 2017).

If you are interested in collaboration please let me know -
I am always looking for people to work with.

An interdisciplinary and collaborative research agenda related to dataflow matrix machines:
dmm-collaborative-research-agenda.pdf (8 pages, March 2021):

- functional reactive programming and program synthesis
- compositional metalearning
- dynamical systems
- trade-offs between synchronous and async
- trade-offs between flexibility and parallelization
- interplay between DMMs and differentiable programming
- fuzzy paraconsistent logic and bicontinuous domains
- probabilistic programming
- real-time visual animation via composition of unit generators
- interplay between DMMs and Transformers
- and more

### Links:

A class of expressive self-modifiable neural machines
- which can fluently modify their own weights, connectivity patterns, and size;
- and can serve as a programming platform, resulting in a programming formalism
with continuously deformable programs.

## Personal interests - late 1990s

Gay mathematicians, queer stuff, eastern philosophy,
Puschino - a Biological Center in Moscow Region,
Jewish intellectual community in Russia, etc.

e-mail: bukatin@cs.brandeis.edu