A maze learning comparison of Elman, long short-term memory, and Mona neural networks
TE Portegys - Neural Networks, 2010 - Elsevier
This study compares the maze learning performance of three artificial neural network
architectures: an Elman recurrent neural network, a long short-term memory (LSTM) network, and …
architectures: an Elman recurrent neural network, a long short-term memory (LSTM) network, and …
Training sensory–motor behavior in the connectome of an artificial C. elegans
TE Portegys - Neurocomputing, 2015 - Elsevier
The Caenorhabditis elegans nematode worm is a small well-known creature, intensely
studied for decades. Its entire morphology has been mapped cell-by-cell, including its 302 …
studied for decades. Its entire morphology has been mapped cell-by-cell, including its 302 …
A search technique for pattern recognition using relative distances
TE Portegys - IEEE Transactions on Pattern Analysis and …, 1995 - ieeexplore.ieee.org
A technique for creating and searching a tree of patterns using relative distances is presented.
The search is conducted to find patterns which are nearest neighbors of a given test …
The search is conducted to find patterns which are nearest neighbors of a given test …
Goal-seeking behavior in a connectionist model
TE Portegys - Artificial Intelligence Review, 2001 - Springer
… The model selected for this project, Mona, was introduced by Portegys (1999) as a connectionist
model of motivation. A connectionist model bears a functional resemblance to a natural …
model of motivation. A connectionist model bears a functional resemblance to a natural …
Data-theoretical synthesis of the early developmental process
Biological development is often described as a dynamic, emergent process. This is evident
across a variety of phenomena, from the temporal organization of cell types in the embryo to …
across a variety of phenomena, from the temporal organization of cell types in the embryo to …
Information isometry technique reveals organizational features in developmental cell lineages
In this paper, we will introduce a method for calculating and visualizing the information content
of embryogenesis called the information isometry technique. We treat cell lineage trees …
of embryogenesis called the information isometry technique. We treat cell lineage trees …
Learning causation event conjunction sequences
TE Portegys - arXiv preprint arXiv:2402.14027, 2024 - arxiv.org
… This project was inspired by Mona (Portegys, 2001), a goal-seeking ANN that composes
hierarchies of cause-and-effect neurons. A method for representing order-independent …
hierarchies of cause-and-effect neurons. A method for representing order-independent …
A connectionist model of motivation
TE Portegys - IJCNN'99. International Joint Conference on …, 1999 - ieeexplore.ieee.org
This paper presents Mona, a connectionist model of motivation implemented by a network
of neuron-like components whose interactions drive behavior toward goals which reduce …
of neuron-like components whose interactions drive behavior toward goals which reduce …
An abstraction of intercellular communication
TE Portegys - Artificial Life: The Proceedings..., 2003 - books.google.com
… Portegys Illinois State University Campus Box 5150 Normal, Illinois, USA 61790-… Portegys
77 … edu/faculty/portegys/research/morphone. zip. The examples described here are viewable …
77 … edu/faculty/portegys/research/morphone. zip. The examples described here are viewable …
Training artificial neural networks to learn a nondeterministic game
TE Portegys - arXiv preprint arXiv:1507.04029, 2015 - arxiv.org
It is well known that artificial neural networks (ANNs) can learn deterministic automata.
Learning nondeterministic automata is another matter. This is important because much of the …
Learning nondeterministic automata is another matter. This is important because much of the …