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"”.

  1. 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 …

    cork Repository record for Theory and applications of multifunctional reservoir computers (opens in a new tab)

  2. 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 …

    maryland Repository record for Combining Physics-based Modeling, Machine Learning, and Data Assimilation for Forecasting Large, Complex, Spatiotemporally Chaotic Systems (opens in a new tab)

  3. 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 …

    mit Repository record for Disordered Optics for Multidimensional Information Processing (opens in a new tab)

  4. 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 …

    maryland Repository record for Efficient and Generalizable Machine Learning Models for Predicting Complex Dynamics (opens in a new tab)

  5. 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 …

    maryland Repository record for Analyzing the Dynamics of Biological and Artificial Neural Networks with Applications to Machine Learning (opens in a new tab)

  6. 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 …

    washington Repository record for A Complex Systems Approach to Understanding Cells as Systems and Agents (opens in a new tab)