A tiny-memory CNN generates part of its weights from a cellular automaton and uses multiplexer-based quantized residual links, reporting up to 1% higher accuracy than two compressed baselines at sub-2Mb sizes.
Reservoir Computing using Cellular Automata
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We introduce a novel framework of reservoir computing. Cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the reservoir. The proposed framework is capable of long short-term memory and it requires orders of magnitude less computation compared to Echo State Networks. Also, for additive cellular automaton rules, reservoir features can be combined using Boolean operations, which provides a direct way for concept building and symbolic processing, and it is much more efficient compared to state-of-the-art approaches.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MOGNET: A Mux-residual quantized Network leveraging Online-Generated weights
A tiny-memory CNN generates part of its weights from a cellular automaton and uses multiplexer-based quantized residual links, reporting up to 1% higher accuracy than two compressed baselines at sub-2Mb sizes.