Results 61 to 70 of about 502,069 (324)
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
Long memory lifetimes require complex synapses and limited sparseness
Frontiers in Computational Neuroscience, 2007 Theoretical studies have shown that memories last longer if the neural representations are sparse, that is, when each neuron is selective for a small fraction of the events creating the memories.
Daniel D Ben Dayan Rubin +3 more
doaj +1 more source
Sparseness-Optimized Feature Importance [PDF]
In this paper, we propose a model-agnostic post-hoc explanation procedure devoted to computing feature attribution. The proposed method, termed Sparseness-Optimized Feature Importance (SOFI), entails solving an optimization problem related to the ...
Nápoles, Gonzalo; id_orcid, Grau, Isel
core +2 more sources
Kernel heterogeneity improves sparseness of natural images representations
Neuromorphic Computing and EngineeringBoth biological and artificial neural networks inherently balance their performance with their operational cost, which characterizes their computational abilities.
Hugo J Ladret +2 more
doaj +1 more source
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
Pediatric Blood &Cancer, EarlyView.ABSTRACT Rates of cancer among adolescents and young adults (AYA), age 15–39 years, are increasing. Consequently, radiation oncologists are treating more AYAs who have diagnoses spanning both pediatric and adult practices. Compared to pediatric and older adult patients, AYAs face a unique set of challenges.
Hesham Elhalawani +7 more
wiley +1 more source
Frontiers in Systems Neuroscience, 2015 The dentate gyrus (DG) of mammals harbors neural stem cells that generate new dentate granule cells (DGCs) throughout life. Behavioral studies using the contextual fear discrimination paradigm have found that selectively augmenting or blocking adult ...
Kathleen Mcavoy, A. Besnard, Amar Sahay
semanticscholar +1 more source
Pediatric Blood &Cancer, EarlyView.ABSTRACT Relapsed and/or refractory (R/R) pediatric acute leukemia carries a dismal prognosis, largely driven by chemoresistance to conventional salvage therapy. The BH3‐mimetic venetoclax, combined with chemotherapy or hypomethylating agents, has demonstrated efficacy in small clinical trials.
Katherine S. Colman +9 more
wiley +1 more source
Nonnegative Matrix Factorization With Data-Guided Constraints For Hyperspectral Unmixing
Remote Sensing, 2017 Hyperspectral unmixing aims to estimate a set of endmembers and corresponding abundances in pixels. Nonnegative matrix factorization (NMF) and its extensions with various constraints have been widely applied to hyperspectral unmixing.
Risheng Huang, Xiaorun Li, Liaoying Zhao
doaj +1 more source
Kernelization and Sparseness: the case of Dominating Set [PDF]
Symposium on Theoretical Aspects of Computer Science, 2014 We prove that for every positive integer $r$ and for every graph class $\mathcal G$ of bounded expansion, the $r$-Dominating Set problem admits a linear kernel on graphs from $\mathcal G$.
P. G. Drange +11 more
semanticscholar +1 more source