From the 1 of 6 linked papers with an AI index.
6 papers
New Synchronous Computation Dynamics for Hopfield Networks
Francisco Requena-DomÃnguez, Rafaela BenÃtez-Rochel, Ezequiel López-Rubio
The paper introduces a new synchronous update rule for Hopfield networks, called SD-DDF, which uses a Discrete Differential Filter to select multiple neurons to update simultaneous…
Instruction Set and Language for Symbolic Regression
Ezequiel Lopez-Rubio, Mario Pascual-Gonzalez
A fundamental but largely unaddressed obstacle in Symbolic regression (SR) is structural redundancy: every expression DAG with admits many distinct node-numbering schemes that all…
Instruction set for the representation of graphs
Ezequiel Lopez-Rubio, Mario Pascual-Gonzalez
We present IsalGraph, a method for representing the structure of any finite, simple graph as a compact string over a nine-character instruction alphabet. The encoding is executed b…
Enhanced QKNorm normalization for neural transformers with the Lp norm
Ezequiel Lopez-Rubio, Javier Montes-Perez, Esteban Jose Palomo
The normalization of query and key vectors is an essential part of the Transformer architecture. It ensures that learning is stable regardless of the scale of these vectors. Some n…
Alternative positional encoding functions for neural transformers
Ezequiel Lopez-Rubio, Macoris Decena-Gimenez, Rafael Marcos Luque-Baena
A key module in neural transformer-based deep architectures is positional encoding. This module enables a suitable way to encode positional information as input for transformer neu…
Representation of the structure of graphs by sequences of instructions
Ezequiel Lopez-Rubio
The representation of graphs is commonly based on the adjacency matrix concept. This formulation is the foundation of most algebraic and computational approaches to graph processin…