Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
-
- Evolutionary computation (2)
- Neural networks (Computer science) (2)
- Biochemical phenomena -- Experiments (1)
- Biomathematics (1)
- Computational complexity (1)
-
- Computational neuroscience (1)
- Data mining (1)
- Decision making -- Statistical methods (1)
- Electric network topology -- Analysis (1)
- Neural networks (Computer science) -- Design and construction (1)
- Pattern recognition systems (1)
- Perceptrons -- Analysis (1)
- Transportation -- Planning -- Oregon -- Portland (1)
Articles 1 - 4 of 4
Full-Text Articles in Physical Sciences and Mathematics
Learning Two-Input Linear And Nonlinear Analog Functions With A Simple Chemical System, Peter Banda, Christof Teuscher
Learning Two-Input Linear And Nonlinear Analog Functions With A Simple Chemical System, Peter Banda, Christof Teuscher
Computer Science Faculty Publications and Presentations
The current biochemical information processing systems behave in a predetermined manner because all features are defined during the design phase. To make such unconventional computing systems reusable and programmable for biomedical applications, adaptation, learning, and self-modification baaed on external stimuli would be highly desirable. However, so far, it haa been too challenging to implement these in real or simulated chemistries. In this paper we extend the chemical perceptron, a model previously proposed by the authors, to function as an analog instead of a binary system. The new analog asymmetric signal perceptron learns through feedback and supports MichaelisMenten kinetics. The results …
Damage Spreading In Spatial And Small-World Random Boolean Networks, Qiming Lu, Christof Teuscher
Damage Spreading In Spatial And Small-World Random Boolean Networks, Qiming Lu, Christof Teuscher
Computer Science Faculty Publications and Presentations
The study of the response of complex dynamical social, biological, or technological networks to external perturbations has numerous applications. Random Boolean networks (RBNs) are commonly used as a simple generic model for certain dynamics of complex systems. Traditionally, RBNs are interconnected randomly and without considering any spatial extension and arrangement of the links and nodes. However, most real-world networks are spatially extended and arranged with regular, power-law, small-world, or other nonrandom connections. Here we explore the RBN network topology between extreme local connections, random small-world, and pure random networks, and study the damage spreading with small perturbations. We find that …
Guiding Data-Driven Transportation Decisions, Kristin A. Tufte, Basem Elazzabi, Nathan Hall, Morgan Harvey, Kath Knobe, David Maier, Veronika Margaret Megler
Guiding Data-Driven Transportation Decisions, Kristin A. Tufte, Basem Elazzabi, Nathan Hall, Morgan Harvey, Kath Knobe, David Maier, Veronika Margaret Megler
Computer Science Faculty Publications and Presentations
Urban transportation professionals are under increasing pressure to perform data-driven decision making and to provide data-driven performance metrics. This pressure comes from sources including the federal government and is driven, in part, by the increased volume and variety of transportation data available. This sudden increase of data is partially a result of improved technology for sensors and mobile devices as well as reduced device and storage costs. However, using this proliferation of data for decisions and performance metrics is proving to be difficult. In this paper, we describe a proposed structure for a system to support data-driven decision making. A …
A Comparative Study Of Reservoir Computing For Temporal Signal Processing, Alireza Goudarzi, Peter Banda, Matthew R. Lakin, Christof Teuscher, Darko Stefanovic
A Comparative Study Of Reservoir Computing For Temporal Signal Processing, Alireza Goudarzi, Peter Banda, Matthew R. Lakin, Christof Teuscher, Darko Stefanovic
Computer Science Faculty Publications and Presentations
Reservoir computing (RC) is a novel approach to time series prediction using recurrent neural networks. In RC, an input signal perturbs the intrinsic dynamics of a medium called a reservoir. A readout layer is then trained to reconstruct a target output from the reservoir's state. The multitude of RC architectures and evaluation metrics poses a challenge to both practitioners and theorists who study the task-solving performance and computational power of RC. In addition, in contrast to traditional computation models, the reservoir is a dynamical system in which computation and memory are inseparable, and therefore hard to analyze. Here, we compare …