Related papers: Optimal coloured perceptrons
A Blume-Emery-Griffiths perceptron model is introduced and its optimal capacity is calculated within the replica-symmetric Gardner approach, as a function of the pattern activity and the imbedding stability parameter. The stability of the…
The thermodynamic and retrieval properties of the Ashkin-Teller neural network model storing an infinite number of patterns are examined in the replica-symmetric mean-field approximation. In particular, for linked patterns…
In this paper, we address the problem of how many randomly labeled patterns can be correctly classified by a single-layer perceptron when the patterns are correlated with each other. In order to solve this problem, two analytical schemes…
The aim of this thesis is to compare the capacity of different models of neural networks. We start by analysing the problem solving capacity of a single perceptron using a simple combinatorial argument. After some observations on the…
The optimal capacity of graded-response perceptrons storing biased and spatially correlated patterns with non-monotonic input-output relations is studied. It is shown that only the structure of the output patterns is important for the…
A p-spin interaction Ashkin-Teller spin glass, with three independent Gaussian probability distributions for the exchange interactions, is studied by means of the replica method. A simple phase diagram is obtained within the…
This paper describes the definition of maximum likelihood equivalent estimators of the Trilinear Gauge Couplings which include detector effects. The asymptotic properties of these estimators as well as their unbiasedness and efficiency when…
A pedagogical introduction to color superconductivity in the weak coupling limit is given. The focus is on the basic tools of thermal field theory necessary to compute observables of color superconductivity. The rich symmetry structure and…
We use the exact scattering description of the scaling Ashkin-Teller model in two dimensions to compute the two-particle form factors of the relevant operators. These provide an approximation for the correlation functions whose accuracy is…
A numerical investigation of a two dimensional integrated fiber grating coupler capable of exciting several LP fiber modes in both TE and TM polarization is presented. Simulation results and an assessment of the numerical complexity of the…
Inference algorithms based on evolving interactions between replicated solutions are introduced and analyzed on a prototypical NP-hard problem - the capacity of the binary Ising perceptron. The efficiency of the algorithm is examined…
This paper presents a novel, model-based compressive antenna design method for high sensing capacity imaging applications. Given a set of design constraints, the method maximizes the sensing capacity of the compressive antenna by varying…
The design space for photonic lanterns is large and complex, making it challenging to identify optimal parameters to achieve specific performances, such as coupling, bandwidth, and insertion loss. Effectively navigating this space requires…
We analyze the collider signatures of models with a vector-like top-prime quark and a massive color-octet boson. The top-prime quark mixes with the top quark in the Standard Model, leading to richer final states than ones that are…
A phenomenological coupled exciton model is proposed in order to characterize optical excitations in extended dendrimers. An onsite exciton state is assigned at each phenyl rings and a nearest neighbor hopping integral which obeys the…
We present an experimental investigation of lumped-element superconducting LC resonators designed to provide different types of coupling to a transmission line. We have designed four resonator geometries including dipole and quadrupole…
An artificial neural network can be used to generate a series of numbers. A boolean perceptron generates bit sequences with a periodic structure. The corresponding spectrum of cycle lengths is investigated analytically and numerically; it…
We study pairwise Ising models for describing the statistics of multi-neuron spike trains, using data from a simulated cortical network. We explore efficient ways of finding the optimal couplings in these models and examine their…
To couple many independent modes from free space to on chip, the key challenge is not enhancing the many necessary coupling rates (scattering-matrix elements) between targeted mode pairs. Instead, the key is to avoid additional…
We study the first-order transition in the model of a simple perceptron with continuous weights and large, bit finite value of the inputs. Making the analogy with the usual finite-size physical systems, we calculate the shift and the…