Related papers: Distribution free uncertainty quantification in ne…

The neural network (NN)-based direct uncertainty quantification (UQ) methods have achieved the state of the art performance since the first inauguration, known as the lower-upper-bound estimation (LUBE) method. However, currently-available…

Conformal prediction is an emerging technique for uncertainty quantification that constructs prediction sets guaranteed to contain the true label with a predefined probability. Recent work develops online conformal prediction methods that…

Uncertainty quantification (UQ) over graphs arises in a number of safety-critical applications in network science. The Gaussian process (GP), as a classical Bayesian framework for UQ, has been developed to handle graph-structured data by…

Bio-inspired Spiking Neural Networks (SNN) are now demonstrating comparable accuracy to intricate convolutional neural networks (CNN), all while delivering remarkable energy and latency efficiency when deployed on neuromorphic hardware. In…

Instantaneous and on demand accuracy-efficiency trade-off has been recently explored in the context of neural networks slimming. In this paper, we propose a flexible quantization strategy, termed Switchable Precision neural Networks…

Spiking Neural Network (SNN), as a brain-inspired and energy-efficient network, is currently facing the pivotal challenge of exploring a suitable and efficient learning framework. The predominant training methodologies, namely…

Spiking neural networks have shown much promise as an energy-efficient alternative to artificial neural networks. However, understanding the impacts of sensor noises and input encodings on the network activity and performance remains…

Brain-inspired Spiking Neural Networks (SNNs) have the characteristics of event-driven and high energy-efficient, which are different from traditional Artificial Neural Networks (ANNs) when deployed on edge devices such as neuromorphic…

Learning operators from data is central to scientific machine learning. While DeepONets are widely used for their ability to handle complex domains, they require fixed sensor numbers and locations, lack mechanisms for uncertainty…

Spiking neural networks (SNNs) are becoming a promising alternative to conventional artificial neural networks (ANNs) due to their rich neural dynamics and the implementation of energy-efficient neuromorphic chips. However, the…

In this PhD thesis, we propose a novel framework for uncertainty quantification in machine learning, which is based on proper scores. Uncertainty quantification is an important cornerstone for trustworthy and reliable machine learning…

Binary spike coding enables sparse and event-driven computation in spiking neural networks (SNNs), yet its 1-bit-per-timestep representation fundamentally limits information throughput. This bottleneck becomes increasingly restrictive in…

Spiking neural networks (SNNs) present a promising computing paradigm for neuromorphic processing of event-based sensor data. The resonate-and-fire (RF) neuron, in particular, appeals through its biological plausibility, complex dynamics,…

Inverse scattering problems, such as those in electromagnetic imaging using phaseless data (PD-ISPs), involve imaging objects using phaseless measurements of wave scattering. Such inverse problems can be highly non-linear and ill-posed…

The deep neural network suffers from many fundamental issues in machine learning. For example, it often gets trapped into a local minimum in training, and its prediction uncertainty is hard to be assessed. To address these issues, we…

Spiking Neural Networks (SNNs) promise orders-of-magnitude lower power consumption and low-latency inference on neuromorphic hardware for a wide range of robotic tasks. In this work, we present an energy-efficient implementation of a…

Bayesian neural networks offer better estimates of model uncertainty compared to frequentist networks. However, inference involving Bayesian models requires multiple instantiations or sampling of the network parameters, requiring…

Quantization is a natural complement to the sparse, event-driven computation of Spiking Neural Networks, reducing memory bandwidth and arithmetic cost for deployment on resource-constrained hardware. However, existing SNN quantization…

Physics-informed neural networks (PINNs) are an influential method of solving differential equations and estimating their parameters given data. However, since they make use of neural networks, they provide only a point estimate of…

Spiking neural networks (SNNs), a brain-inspired computing paradigm, are emerging for their inference performance, particularly in terms of energy efficiency and latency attributed to the plasticity in signal processing. To deploy SNNs in…