Related papers: Artificial Neural Network for Constructing Type Ia…

Person re-identification (reID) benefits greatly from deep convolutional neural networks (CNNs) which learn robust feature embeddings. However, CNNs are inherently limited in modeling the large variations in person pose and scale due to…

Iterative approximation methods using backpropagation enable the optimization of neural networks, but they remain computationally expensive, especially when used at scale. This paper presents an efficient alternative for optimizing neural…

The model parameters of convolutional neural networks (CNNs) are determined by backpropagation (BP). In this work, we propose an interpretable feedforward (FF) design without any BP as a reference. The FF design adopts a data-centric…

We present AURA-net, a convolutional neural network (CNN) for the segmentation of phase-contrast microscopy images. AURA-net uses transfer learning to accelerate training and Attention mechanisms to help the network focus on relevant image…

An object-oriented approach to implementing artificial neural networks is introduced in this article. The networks obtained in this way are highly connected in that they admit edges between nodes in any layers of the network, and dynamic,…

A method is presented for automated photometric classification of supernovae (SNe) as Type-Ia or non-Ia. A two-step approach is adopted in which: (i) the SN lightcurve flux measurements in each observing filter are fitted separately; and…

Deploying neural networks to different devices or platforms is in general challenging, especially when the model size is large or model complexity is high. Although there exist ways for model pruning or distillation, it is typically…

Observations of type Ia supernovae (SNe Ia) have led to suggestions of multiple progenitor and explosion scenarios. Distinguishing between scenarios and tying specific SNe Ia to individual scenarios however has so far been challenging.…

Artificial neural networks are trained by a standard backpropagation learning algorithm with regularization to model and predict the systematics of -decay of heavy and superheavy nuclei. This approach to regression is implemented in two…

Type Ia supernovae are an important tool for studying the expansion history of the universe. Advancing our yet incomplete understanding of the explosion scenario requires detailed and realistic numerical models in order to interpret and…

This is the first release of optical spectroscopic data of low-redshift Type Ia supernovae (SNe Ia) by the Carnegie Supernova Project including 604 previously unpublished spectra of 93 SNe Ia. The observations cover a range of phases from…

We use a Convolutional Recurrent Neural Network approach to learn morphological evolution driven by surface diffusion. To this aim we first produce a training set using phase field simulations. Intentionally, we insert in such a set only…

A feed-forward neural network is demonstrated to efficiently unfold the energy distribution of protons and alpha particles passing through passive material. This model-independent approach works with unbinned data and does not require…

Merging white dwarfs are a possible progenitor of Type Ia supernovae (SNe Ia). While it is not entirely clear if and when an explosion is triggered in such systems, numerical models suggest that a detonation might be initiated before the…

Using light curves and host galaxy spectra of 101 Type Ia supernovae (SNe Ia) with redshift $z \lesssim 0.3$ from the SDSS Supernova Survey (SDSS-SN), we derive the SN Ia rate as a function of progenitor age (the delay time distribution, or…

We use a new technique to extract the spectrum of a supernova from that of the contaminating background of its host galaxy, and apply it to the specific case of high-redshift Type Ia supernova (SN Ia) spectroscopy. The algorithm is based on…

Type Ia supernovae are generally agreed to arise from thermonuclear explosions of carbon-oxygen white dwarfs. The actual path to explosion, however, remains elusive, with numerous plausible parent systems and explosion mechanisms suggested.…

We propose a novel approach for a machine-learning-based detection of the type Ia supernovae using photometric information. Unlike other approaches, only real observation data is used during training. Despite being trained on a relatively…

Convolutional Neural Networks (CNNs) are a class of artificial neural networks whose computational blocks use convolution, together with other linear and non-linear operations, to perform classification or regression. This paper explores…

The classic single-degenerate model for the progenitors of Type Ia Supernova (SN Ia) predicts that the supernova ejecta should be enriched with solar-like abundance material stripped from the companion star. Spectroscopic observations of…