Compressed feature vector-based effective object recognition model in detection of COVID-19. [PDF]
Pattern Recognit Lett, 2022 Chen C +5 more
europepmc +1 more source
Communication Efficient Algorithms for Bounding and Approximating the Empirical Entropy in Distributed Systems. [PDF]
Entropy (Basel), 2022 Shahar A, Alfassi Y, Keren D.
europepmc +1 more source
A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs [PDF]
How does the geometric representation of a dataset change after the application of each randomly initialized layer of a neural network? The celebrated Johnson-Lindenstrauss lemma answers this question for linear fully-connected neural networks (FNNs ...
Khina, Anatoly +3 more
core +1 more source
Simple, unified analysis of Johnson-Lindenstrauss with applications [PDF]
We present a simplified and unified analysis of the Johnson-Lindenstrauss (JL) lemma, a cornerstone of dimensionality reduction for managing high-dimensional data.
Li, Yingru
core +1 more source
Fast, low-memory detection and localization of large, polymorphic inversions from SNPs. [PDF]
PeerJ, 2022 Nowling RJ +6 more
europepmc +1 more source
SHARP: hyperfast and accurate processing of single-cell RNA-seq data via ensemble random projection. [PDF]
Genome Res, 2020 Wan S, Kim J, Won KJ.
europepmc +1 more source
CALIBRATIONLESS MRI RECONSTRUCTION WITH A PLUG-IN DENOISER. [PDF]
Proc IEEE Int Symp Biomed Imaging, 2021 Zhao S, Potter LC, Ahmad R.
europepmc +1 more source
Neural manifold analysis of brain circuit dynamics in health and disease. [PDF]
J Comput Neurosci, 2023 Mitchell-Heggs R +4 more
europepmc +1 more source
Stochastic quasi-gradient methods: variance reduction via Jacobian sketching. [PDF]
Math Program, 2021 Gower RM, Richtárik P, Bach F.
europepmc +1 more source
The Performance of Johnson-Lindenstrauss Transforms: Beyond the Classical Framework
, 2020 Euclidean dimensionality reduction is a commonly used technique to scale up algorithms in machine learning and data science. The goal of Euclidean dimensionality reduction is to reduce the dimensionality of a dataset, while preserving Euclidean distances
Jagadeesan, Meena
core