Results 41 to 50 of about 724,897 (308)
Explicit Object Representation by Sparse Neural Codes [PDF]
, 2008 Neurons have been identified in the human medial temporal lobe (MTL) that display a strong selectivity for only a few stimuli (such as familiar individuals or landmark buildings) out of perhaps 100 presented to the test subject.
Waydo, Stephen J.
core +1 more source
CederGroupHub/sparse-lm: v0.5.0
, 2023 What's Changed Allow adding constraints by @lbluque in https://github.com/CederGroupHub/sparse-lm/pull/88 Updates and fixes by @lbluque in https://github.com/CederGroupHub/sparse-lm/pull/93 Full Changelog: https://github.com/CederGroupHub/sparse-lm ...
Peichen Zhong +4 more
core +1 more source
Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference
CoRR, 2019 Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes. Different from most existing methods that require and
Shun Liao +4 more
openaire +2 more sources
Scottish Journal of Political Economy, 2023 ABSTRACT Forecasting economic activity during institutional collapse requires nowcasts derived exclusively from alternative data sources. Such sources are abundant yet theoretically unanchored and potentially weakly informative. This study examines whether sparse supervised dimension reduction extracts reliable signals in a context ...
openaire +2 more sources
Bayesian Orthogonal Component Analysis for Sparse Representation [PDF]
, 2010 This paper addresses the problem of identifying a lower dimensional space where observed data can be sparsely represented. This undercomplete dictionary learning task can be formulated as a blind separation problem of sparse sources linearly mixed with ...
Nicolas Dobigeon +3 more
core +1 more source
Stabilized Sparse Online Learning for Sparse Data
J. Mach. Learn. Res., 2016 45 pages, 4 ...
Yuting Ma, Tian Zheng
openaire +4 more sources
Improved sparse representation using adaptive spatial support for effective target detection in hyperspectral imagery [PDF]
, 2013 With increasing applications of hyperspectral imagery (HSI) in agriculture, mineralogy, military, and other fields, one of the fundamental tasks is accurate detection of the target of interest.
Li, Xiaohui +3 more
core +3 more sources
SSRN Electronic Journal, 2014 Cointegration analysis is used to estimate the long-run equilibrium relations between several time series. The coefficients of these long-run equilibrium relations are the cointegrating vectors. In this paper, we provide a sparse estimator of the cointegrating vectors.
Wilms, Ines, Croux, Christophe
openaire +2 more sources
Adaptive sparse tiling for sparse matrix multiplication [PDF]
Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming, 2019 Tiling is a key technique for data locality optimization and is widely used in high-performance implementations of dense matrix-matrix multiplication for multicore/manycore CPUs and GPUs. However, the irregular and matrix-dependent data access pattern of sparse matrix multiplication makes it challenging to use tiling to enhance data reuse.
Changwan Hong +4 more
openaire +1 more source
Yankuang ceshiSince the cathode material of selenium hollow cathode lamps is a lead–selenium alloy, it can simultaneously excite characteristic spectral lines for both lead and selenium.
Weikang HU +4 more
doaj +1 more source