Auteurs : Mitja Peruš https://popups.uliege.be/3041-539x/index.php?id=1325 Publications of Auteurs Mitja Peruš fr 0 A Computational Study of Reconstruction (from Partial Data) and Anticipation Capabilities of an Associative Neural Net with Large Stored Data-Base https://popups.uliege.be/3041-539x/index.php?id=4559 I simulated a large Hopfield neural net which had the signum instead of sigmoid activation function so that it could be naturally physically implemented, e.g. in spin systems. It has been used in computational simulations in order to analyze the following capabilities of processing very large and complex data sets (e.g., protein-structure data-bases): 1. completion of patterns; 2. recognition of patterns; 3. prediction of unknown parameters; 4. a.nticipation. While for tasks 1-3 we use a memory-ba,se of previouslylearned examples using "a,ssociations", ta.sk 4 is equivalent to case 3 re-interpreted for temporal (or timeseries) prediction, i.e. prediction of unknown future parameter-values (instead of unknown present ones). For tasks 3 and 4 it is concluded that a generalization of the model used in simulation, like phase-Hebb processing or quantum-like information dynamics, if more promising. Data-structure conditions for success of tasks l-4 are discussed in a complex "real-life" example. Mon, 14 Oct 2024 11:35:24 +0200 Mon, 14 Oct 2024 13:02:15 +0200 https://popups.uliege.be/3041-539x/index.php?id=4559 The Most Natural Procedure for Quantum Image Recognition https://popups.uliege.be/3041-539x/index.php?id=2395 It is shown how images can be processed, memorized, reconstructed or/and recognized using fundamental and relatively non-artificial quantum dynamics, i.e. | Ψ) =| Ψ)(Ψ | Ψ) in Dirac's notation. The right-most | Ψ) represents the output, the left-most | Ψ) denotes the input, and the central | Ψ)( Ψ | represents the associative memory. No quantum logic gates are needed, but merely a holographic procedure. Our computational model, successfully tested on concrete data, is a quantum version of Hopfield-based neural-netlike associative processing which is mathematicaliy translated into wave-dynamics in a straight-forward way. Here we discuss its most natural quantum implementation(s), i.e. using ordinary interference of image-modulated quantum waves. The non-trivial (even, e.g., anticipatory) capabilities of this model arise from proper consideration of data-structure, or pre-processing by classical systems, therefore it is the best available candidate for the quantum kernel of (conscious) image recognition in the visual cortex. Thu, 08 Aug 2024 10:01:15 +0200 Thu, 08 Aug 2024 10:01:31 +0200 https://popups.uliege.be/3041-539x/index.php?id=2395 A Synthesis of the Pribram Holonomic Theory of Vision With Quantum Associative Nets After Pre-Processing Using I.C.A. and Other Computational Models https://popups.uliege.be/3041-539x/index.php?id=1319 Statistically-Independent Component Analysis (ICA) and sparseness-maximization net are models which maximally preserve information ("infomax"). Research of relevance of these algorithms for modeling image-processing in V1 is reported in comparison with the Holonomic Brain Theory by Pribram which advocates dendritic processing and its connection to quantum processing. "Infomax" models are presented and discussed as a possible early-processing gateway to higher visual processing involving quantum associative nets (Perus, 2000) and attractor dynamics. Wed, 10 Jul 2024 10:53:14 +0200 Wed, 10 Jul 2024 10:53:23 +0200 https://popups.uliege.be/3041-539x/index.php?id=1319