Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 6 of 6 for “"reservoir computers"”.
-
Theory and applications of multifunctional reservoir computers
… biological to artificial neural networks via the reservoir computing machine learning paradigm. Multifunctionality describes the ability of a single neural network that exploits a form of multistability to perform a multitude of mutually exclusive tasks. The dynamics of multifunctional RCs are …
-
Combining Physics-based Modeling, Machine Learning, and Data Assimilation for Forecasting Large, Complex, Spatiotemporally Chaotic Systems
… a parallel ML architecture consisting of many reservoir computers and trained using complete observations of the system's past evolution. Using the Kuramoto-Sivashinsky equation as our test model, we demonstrate that this technique produces more accurate short-term forecasts than either the …
-
Disordered Optics for Multidimensional Information Processing
… second part of the thesis is about scattering reservoir computers (RC). Complex optical medium shows great potential for large-scale optical RC thanks to the intrinsic parallelism and scalability. We identify the trade-off between the fading memory and non-normality of scattering RC, which …
-
Efficient and Generalizable Machine Learning Models for Predicting Complex Dynamics
… data. In this dissertation, we first show that reservoir computing—a simple, efficient, and versatile framework for data-driven modeling of dynamical systems—can generalize to unexplored regions of state space without explicit structural priors. Using multistable dynamical systems as a test …
-
Analyzing the Dynamics of Biological and Artificial Neural Networks with Applications to Machine Learning
… networks in the brain, within the framework of reservoir computing. We emphasize the stabilizing role of inhibition in reservoir computers (RCs), mirroring its function in the brain. We propose a novel inhibitory adaptation mechanism that allows RCs to autonomously adjust inhibitory connections …
-
A Complex Systems Approach to Understanding Cells as Systems and Agents
… behavior in cellular populations. Using a BN reservoir computer model of cellular signal processing, I find that flexibility in signal processing is guaranteed if enough cellular resources (e.g., number of nodes) are available; however, fewer resources could attain flexibility, but with lower …