Related papers: Artificial Neural Network for Constructing Type Ia…

Convolutional neural networks have achieved great success in various vision tasks; however, they incur heavy resource costs. By using deeper and wider networks, network accuracy can be improved rapidly. However, in an environment with…

Purpose: We propose a novel method for continual learning based on the increasing depth of neural networks. This work explores whether extending neural network depth may be beneficial in a life-long learning setting. Methods: We propose a…

In the era of large all-sky surveys, there will be a need for rapid, automatic classifications of newly discovered transient objects. Our focus here is the classification of supernovae (SNe). We consider random forest machine learning…

Redshift measurement has always been a constant need in modern astronomy and cosmology. And as new surveys have been providing an immense amount of data on astronomical objects, the need to process such data automatically proves to be…

After correcting for their light-curve shape and color, Type Ia supernovae (SNe Ia) are precise cosmological distance indicators. However, there remains a non-zero intrinsic scatter in the differences between measured distance and that…

Accounting for selection effects in supernova type Ia (SN Ia) cosmology is crucial for unbiased cosmological parameter inference -- even more so for the next generation of large, mostly photometric-only surveys. The conventional "bias…

We present late-time spectra of eight Type Ia supernovae (SNe Ia) obtained at $>200$ days after peak brightness using the Gemini South and Keck telescopes. All of the SNe Ia in our sample were nearby, well separated from their host galaxy's…

We construct spectra of supernovae interacting strongly with a circumstellar medium (CSM) by adding SN templates, a black-body continuum and an emission-line spectrum. In a Monte Carlo simulation we generate more than 800 spectra,…

We present spectra for 14 high-redshift (0.17 < z < 0.83) supernovae, which were discovered by the Supernova Cosmology Project as part of a campaign to measure cosmological parameters. The spectra are used to determine the redshift and…

We present nine near-infrared (NIR) spectra of supernova (SN) 2005cf at epochs from -10 d to +42 d with respect to B-band maximum, complementing the existing excellent data sets available for this prototypical Type Ia SN at other…

Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn new tasks and overcome forgetting the knowledge obtained from the…

The study of Type Ia supernovae (SNIa) has lead to greatly improved insights into many fields in astrophysics, however a theoretical explanation of the origin of these events is still lacking. We investigate the potential contribution to…

We introduce SuperNNova, an open source supernova photometric classification framework which leverages recent advances in deep neural networks. Our core algorithm is a recurrent neural network (RNN) that is trained to classify light-curves…

Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems. Backpropagation through time is the algorithm that is commonly used to train…

Interpreting how does deep neural networks (DNNs) make predictions is a vital field in artificial intelligence, which hinders wide applications of DNNs. Visualization of learned representations helps we humans understand the vision of DNNs.…

This paper has proposed a new baseline deep learning model of more benefits for image classification. Different from the convolutional neural network(CNN) practice where filters are trained by back propagation to represent different…

The goal of this document is to provide a pedagogical introduction to the main concepts underpinning the training of deep neural networks using gradient descent; a process known as backpropagation. Although we focus on a very influential…

In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections…

The topology of artificial neural networks has a significant effect on their performance. Characterizing efficient topology is a field of promising research in Artificial Intelligence. However, it is not a trivial task and it is mainly…

Type Ia supernovae remain poorly understood despite decades of investigation. Massive computationally intensive hydrodynamic simulations have been developed and run to model an ever-growing number of proposed progenitor channels. Further…