Scalable Extreme Deconvolution
The Extreme Deconvolution method fits a probability density to a dataset where each observation has Gaussian noise added with a known sample-specific covariance, originally intended for use with astronomical datasets. The existing fitting method is batch EM, which would not normally be applied to large datasets such as the Gaia catalog containing noisy observations of a billion stars. We propose two minibatch variants of extreme deconvolution, based on an online variation of the EM algorithm, and direct gradient-based optimisation of the log-likelihood, both of which can run on GPUs. We demonstrate that these methods provide faster fitting, whilst being able to scale to much larger models for use with larger datasets.
Code (1)
Similar Papers 제목 키워드 기반
A Unified Hardware Architecture for Convolutions and Deconvolutions in CNN
In this paper, a scalable neural network hardware architecture for image segmentation is proposed. By sharing the same computing resources, both convolution and deconvolution operations are handled by the same process el…
Image SegmentationSemantic SegmentationA Deep Optimization Approach for Image Deconvolution
In blind image deconvolution, priors are often leveraged to constrain the solution space, so as to alleviate the under-determinacy. Priors which are trained separately from the task of deconvolution tend to be instable, …
Image DeconvolutionA Clearer Picture of Blind Deconvolution
Blind deconvolution is the problem of recovering a sharp image and a blur kernel from a noisy blurry image. Recently, there has been a significant effort on understanding the basic mechanisms to solve blind deconvolution…
A Design Methodology for Efficient Implementation of Deconvolutional Neural Networks on an FPGA
In recent years deep learning algorithms have shown extremely high performance on machine learning tasks such as image classification and speech recognition. In support of such applications, various FPGA accelerator arch…
CPUDenoisingGeneral ClassificationGenerative Adversarial Network+8Super-resolution with Binary Priors: Theory and Algorithms
The problem of super-resolution is concerned with the reconstruction of temporally/spatially localized events (or spikes) from samples of their convolution with a low-pass filter. Distinct from prior works which exploit …
Super-Resolution