Related papers: Broad Absorption Line Quasar catalogues with Super…
We present a statistical analysis of the associated, high ionization narrow absorption line (NAL) systems in a sample of 59 QSOs defined from the HST QSO Absorption Line Key Project. We have compiled the QSO luminosities at 2500 A, 5 GHz,…
We introduce implicit Bayesian neural networks, a simple and scalable approach for uncertainty representation in deep learning. Standard Bayesian approach to deep learning requires the impractical inference of the posterior distribution…
Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in $\mathbb{R}^d$ are `bound' together to produce a new vector in the same space. VSAs support the commutativity and associativity of…
We review observations of molecular absorption line systems at high redshift toward red quasars and gravitational lenses.
Network quantization is an effective solution to compress deep neural networks for practical usage. Existing network quantization methods cannot sufficiently exploit the depth information to generate low-bit compressed network. In this…
Machine learning (ML) and deep learning (DL) techniques are increasingly used across astrophysics, enabled by the growing availability of data and improved acquisition methods. These approaches now support tasks from redshift estimation to…
Bayesian optimization (BO) provides a powerful framework for optimizing black-box, expensive-to-evaluate functions. It is therefore an attractive tool for engineering design problems, typically involving multiple objectives. Thanks to the…
Deep learning has enjoyed tremendous success in a variety of applications but its application to quantile regressions remains scarce. A major advantage of the deep learning approach is its flexibility to model complex data in a more…
Quasars can be used to measure baryon acoustic oscillations at high redshift, which are considered as direct tracers of the most distant large-scale structures in the Universe. It is fundamental to select quasars from observations before…
Deep neural networks have achieved state-of-the art performance on various computer vision tasks. However, their deployment on resource-constrained devices has been hindered due to their high computational and storage complexity. While…
A kernel-based quantum classifier is the most practical and influential quantum machine learning technique for the hyper-linear classification of complex data. We propose a Variational Quantum Approximate Support Vector Machine (VQASVM)…
Nonlinear methods such as Deep Neural Networks (DNNs) are the gold standard for various challenging machine learning problems, e.g., image classification, natural language processing or human action recognition. Although these methods…
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging problems. However, since deep learning methods operate as black boxes, the uncertainty associated with their predictions is often…
The deep neural networks (DNNs) have achieved great success in learning complex patterns with strong predictive power, but they are often thought of as "black box" models without a sufficient level of transparency and interpretability. It…
Broad Absorption Line Quasars (BALQs) generally exhibit significant outflows that may interact with the surrounding medium, resulting in radio emission. We selected a sample of 13 powerful radio-quiet (RQ) BALQs, where the UV outflow…
Bayesian neural networks (BNNs) have been long considered an ideal, yet unscalable solution for improving the robustness and the predictive uncertainty of deep neural networks. While they could capture more accurately the posterior…
Binary Neural Networks (BiNNs), which employ single-bit precision weights, have emerged as a promising solution to reduce memory usage and power consumption while maintaining competitive performance in large-scale systems. However, training…
This paper describes Macquarie University's contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document…
This paper develops a randomized approach for incrementally building deep neural networks, where a supervisory mechanism is proposed to constrain the random assignment of the weights and biases, and all the hidden layers have direct links…
We review recent results on quasars from the SDSS as they relate to our understanding of the UV/optical continuum, the broad emission line region, and the broad absorption line region. The ensemble average colors of large numbers of quasars…