Related papers: Deep Sturm--Liouville: From Sample-Based to 1D Reg…

Multi Task Learning (MTL) efficiently leverages useful information contained in multiple related tasks to help improve the generalization performance of all tasks. This article conducts a large dimensional analysis of a simple but, as we…

Artificial Neuronal Networks are models widely used for many scientific tasks. One of the well-known field of application is the approximation of high-dimensional problems via Deep Learning. In the present paper we investigate the Deep…

Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to the input, which undermines their true practicality. Recent…

We introduce a new algorithm, Regression based Supervised Learning (RSL), for learning per instance Neural Network (NN) defined heuristic functions for classical planning problems. RSL uses regression to select relevant sets of states at a…

Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the DNNs could be trained in low-dimensional subspaces. In this paper, we propose a Dynamic Linear Dimensionality Reduction…

Deep learning (DL) has transformed applications in a variety of domains, including computer vision, natural language processing, and tabular data analysis. The search for improved DL model accuracy has led practitioners to explore…

Self-supervised learning (SSL) has emerged as a promising solution for addressing the challenge of limited labeled data in deep neural networks (DNNs), offering scalability potential. However, the impact of design dependencies within the…

As a non-linear extension of the classic Linear Discriminant Analysis(LDA), Deep Linear Discriminant Analysis(DLDA) replaces the original Categorical Cross Entropy(CCE) loss function with eigenvalue-based loss function to make a deep neural…

On-device machine learning (ODML) enables intelligent applications on resource-constrained devices. However, power consumption poses a major challenge, forcing a trade-off between model accuracy and power efficiency that often limits model…

Generalisation of a deep neural network (DNN) is one major concern when employing the deep learning approach for solving practical problems. In this paper we propose a new technique, named approximated orthonormal normalisation (AON), to…

Deep learning (DL)-based models have demonstrated good performance in medical image segmentation. However, the models trained on a known dataset often fail when performed on an unseen dataset collected from different centers, vendors and…

In this paper we consider Deep Neural Networks (DNNs) with a smooth activation function as surrogates for high-dimensional functions that are somewhat smooth but costly to evaluate. We consider the standard (non-periodic) DNNs as well as…

In this study, we define discrete fractional Sturm-Liouville (DFSL) operators within Riemann-Liouville and Gr\"unwald-Letnikov fractional operators with both delta and nabla operators. We show selfadjointness of the DFSL operator for the…

In this work, we consider direction-of-arrival (DoA) estimation in the presence of extreme noise using Deep Learning (DL). In particular, we introduce a Convolutional Neural Network (CNN) that is trained from mutli-channel data of the true…

Algorithmic Differentiation (AD) can be used to automate the generation of derivatives in arbitrary software projects. This will generate maintainable derivatives, that are always consistent with the computation of the software. If a domain…

Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient over their predecessors. However, there is a lack of an efficient and generalized training method for deep SNNs, especially for deployment on…

Deep Convolutional Neural Network (DCNN) and Transformer have achieved remarkable successes in image recognition. However, their performance in fine-grained image recognition is still difficult to meet the requirements of actual needs. This…

We develop a declarative DSL - \cf - that can be used to specify Abstract Interpretation-based DNN certifiers. In \cf, programmers can easily define various existing and new abstract domains and transformers, all within just a few 10s of…

Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may…

We study the theory of neural network (NN) from the lens of classical nonparametric regression problems with a focus on NN's ability to adaptively estimate functions with heterogeneous smoothness -- a property of functions in Besov or…