Group actions and learning for a family of automata
A study of the dynamics of a family of artificial neural networks (ANN) is presented based on a new method, that of the action of the group of isometries of the state space (hypercube). This group is generated by two kinds of isometries: permutation of two coordinates of a state and sign invertion of one coordinate. After a short review of the Hopfield initial model for content adressable memory there are presented some of its generalizations and several of learning algorithms, i.e., determining interconnection weights knowing the stable points of ANN. In the main section of the paper the new method is presented and it is shown that most of the learning algorithms are invariant under the action of defined isometries. Also it is proved on what conditions this invariance takes place, and what is the general structure of the space of states of an ANN. In the next section a simple application of a theorem proved in the previous section, about the structure of the space of stable points, is presented. Results are derived about an upper bound on the number of stable states for a particular ANN having as learning algorithm the sum of outer products of degree 2. The last section on concluding remarks presents some of possible further work in the field and a proposal for some practical applications. The paper ends with an appendix in which several formal properties are listed that are relevant for learning rules.
- scientific article; zbMATH DE number 3551942 (Why is no real title available?)
- Neural network design for efficient information retrieval
- Neural networks and physical systems with emergent collective computational abilities
- Neural networks, orientations of the hypercube, and algebraic threshold functions
- On optimal nonlinear associative recall
- Symmetries in neural networks: a linear group action approach
- Polynomial threshold functions, hyperplane arrangements, and random tensors
- Automatically Defined Groups for Knowledge Acquisition from Computer Logs and Its Extension for Adaptive Agent Size
- On permutation symmetries of Hopfield model neural network
- Dynamical properties of a perceptron learning process: structural stability under numerics and shadowing
- On partial groupoids associated with the composition of multilayer feedforward neural networks
This page was built for publication: Group actions and learning for a family of automata
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1109570)
