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 16 of 16 for “"BNNs"”.

  1. Priors in finite and infinite Bayesian convolutional neural networks

    Bayesian neural networks (BNNs) have undergone many changes since the seminal work of Neal [Nea96]. Advances in approximate inference and the use of GPUs have scaled BNNs to larger data sets, and much higher layer and parameter counts. Yet, the priors used for BNN parameters have remained …

    cambridge Repository record for Priors in finite and infinite Bayesian convolutional neural networks (opens in a new tab)

  2. Towards Reliable AI via Efficient Verification of Binarized Neural Networks

    … In this context, Binarized Neural Networks (BNNs) are attractive because they work with quantized inputs and binarized internal activation and weight values and thus support verification free of floating point error. The binarized computation of BNNs directly corresponds to logical reasoning. …

    mit Repository record for Towards Reliable AI via Efficient Verification of Binarized Neural Networks (opens in a new tab)

  3. Uncertainty in Neural Networks; Bayesian Ensembles, Priors & Prediction Intervals

    … in this thesis relate to Bayesian NNs (BNNs). Specifying appropriate priors is an important step in any Bayesian model, yet it is not clear how to do this in BNNs. The first contribution shows that the connection between BNNs and Gaussian Processes (GPs) provides an effective lens to …

    cambridge Repository record for Uncertainty in Neural Networks; Bayesian Ensembles, Priors & Prediction Intervals (opens in a new tab)

  4. The synthesis, characterization, and application of carborane-cluster based macrocycles and boron nitride nanosheets in photovoltaics

    … functionalization of boron nitride nanosheets (BNNS) with polythiophene can produce a working photovoltaic device when attached to TiO2 nanoparticles as a semiconductor in a manner similar to a DSSC. This paper explores the characterizations of a new polythiophene-BNNS complex, as well as …

    syracuse-diss Repository record for The synthesis, characterization, and application of carborane-cluster based macrocycles and boron nitride nanosheets in photovoltaics (opens in a new tab)

  5. Connectome-Constrained Artificial Neural Networks

    In biological neural networks (BNNs), structure provides a set of guard rails by which function is constrained to solve tasks effectively, handle multiple stimuli simultaneously, adapt to noise and input variations, and preserve energy expenditure. Such features are desirable for artificial neural …

    uwo Repository record for Connectome-Constrained Artificial Neural Networks (opens in a new tab)

  6. Multi-Level Quantization of Stochastic Variational Inference based Bayesian Neural Networks

    Bayesian Neural Networks (BNNs) integrate the representational power of standard neural networks with the uncertainty estimation capabilities of Bayesian Inference, offering a robust framework to address challenges such as overconfidence and overfitting. However, the inherent complexity of BNNs

    heid-thes Repository record for Multi-Level Quantization of Stochastic Variational Inference based Bayesian Neural Networks (opens in a new tab)

  7. Improved Sampling and Variational Inference Methods for Neural Networks

    Bayesian Neural Networks (BNNs), an application of Bayesian inference to neural networks, offer an alternative way of training. They combine multiple weight settings, each compatible with the training data, and quantify the uncertainty about the network's weights. While Bayesian inference applied …

    cambridge Repository record for Improved Sampling and Variational Inference Methods for Neural Networks (opens in a new tab)

  8. Bayesian Neural Networks for Actuarial Mortality Modelling

    The use of Bayesian neural networks (BNNs) for mortality modelling is an understudied, yet potentially promising area of research. They inherently offer robust uncertainty quantification, and are known for their application to sparse or small datasets. This research investigates the efficacy of BNN …

    stellenbosch Repository record for Bayesian Neural Networks for Actuarial Mortality Modelling (opens in a new tab)

  9. Efficient Ensemble-based Bayesian Neural Networks for Depth Regression

    … in the training data. Bayesian Neural Networks (BNNs) extend the capabilities of traditional NNs by modeling uncertainty in their predictions. Since analytical Bayesian inference is often intractable for high-dimensional NNs, approximate approaches are used to realize BNNs. Monte Carlo Dropout …

    heid-thes Repository record for Efficient Ensemble-based Bayesian Neural Networks for Depth Regression (opens in a new tab)

  10. Thermal and photochemical reactions of large metallaborane clusters and functionalizations of boron nitride nanosheets

    … and solubilization of boron nitride nanosheets (BNNSs) has been achieved by using polythiophene or polyvinylpyrrolidone as a functionalization polymer with BNNSs. The BNNSs form strong π-π stacking interactions with the polythiophenes and were found to act as a bandgap tuning tool for …

    syracuse-diss Repository record for Thermal and photochemical reactions of large metallaborane clusters and functionalizations of boron nitride nanosheets (opens in a new tab)

  11. Audio computing in the wild: frameworks for big data and small computers

    … test time are defined with Boolean algebra, too. BNNs are spatially and computationally efficient in implementations, since (a) we represent a real-valued sample or parameter with a bit (b) the multiplication and addition correspond to bitwise XNOR and bit-counting, respectively. Therefore, BNNs

    uiuc Repository record for Audio computing in the wild: frameworks for big data and small computers (opens in a new tab)

  12. Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies

    … As a key example, Bayesian Neural Networks (BNNs) are one of the most successful Bayesian models being increasingly employed in a wide range of real-world AI applications which demand reliable and robust decisions. However, the nature of BNN stochastic inference and training procedures incurs …

    houston Repository record for Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies (opens in a new tab)

  13. Bayesian Learning for Data-Efficient Control

    … of high-dimensional control is possible as BNNs scale to high-dimensional state inputs.

    cambridge Repository record for Bayesian Learning for Data-Efficient Control (opens in a new tab)

  14. Multimodal Probabilistic Inference for Robust Uncertainty Quantification

    … baselines in terms of accuracy. Furthermore, BNNs underperform deep ensembles as they fail to explore multiple modes, in the loss space, while being effective at capturing uncertainty within a single mode.</p><p>In this thesis, we develop multimodal representations of model uncertainty that …

    duke Repository record for Multimodal Probabilistic Inference for Robust Uncertainty Quantification (opens in a new tab)

  15. Computing over in-vitro predictive coding neural cultures

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms

    uiuc Repository record for Computing over in-vitro predictive coding neural cultures (opens in a new tab)

  16. Towards Robust Deep Neural Networks

    … a principled method of adversarially training BNNs. Recognising the threat from backdoor or Trojan attacks against DNNs, the research considers the problem of finding a robust defence method that is effective against Trojan attacks. The research explores a new idea in the domain; sanitisation …

    adelaide Repository record for Towards Robust Deep Neural Networks (opens in a new tab)