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"”.
-
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 …
-
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. …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
Bayesian Learning for Data-Efficient Control
… of high-dimensional control is possible as BNNs scale to high-dimensional state inputs.
-
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 …
-
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
-
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 …