Home /
Research
Showing 127 - 132 / 897
Efficient Low Rank Gaussian Variational Inference for Neural Networks
MarcinTomczak, SiddharthSwaroop, RichardTurner....
Published date-12/01/2020
VariationalInference
Bayesian neural networks are enjoying a renaissance driven in part by recent advances in variational inference (VI). The most common form of VI employs a fully factorized or mean-field distribution, …
On Statistical Analysis of MOEAs with Multiple Performance Indicators
HaoWang, CarlosIgncioHernándezCastellanos, TomeEftimov....
Published date-12/01/2020
Assessing the empirical performance of Multi-Objective Evolutionary Algorithms (MOEAs) is vital when we extensively test a set of MOEAs and aim to determine a proper ranking thereof. Multiple performance indicators, …
Unsupervised Anomaly Detection From Semantic Similarity Scores
NimaRafiee, RahilGholamipoor, MarkusKollmann....
Published date-12/01/2020
AnomalyDetection, Out-of-DistributionDetection, SemanticSimilarity, SemanticTextualSimilarity, UnsupervisedAnomalyDetection
In this paper, we present SemSAD, a simple and generic framework for detecting examples that lie out-of-distribution (OOD) for a given training set. The approach is based on learning a …
Baxter Permutation Process
MasahiroNakano, AkisatoKimura, TakeshiYamada....
Published date-12/01/2020
BayesianInference
In this paper, a Bayesian nonparametric (BNP) model for Baxter permutations (BPs), termed BP process (BPP) is proposed and applied to relational data analysis. The BPs are a well-studied class …
The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification
YihaoLv, YouzhiGu, LiuXinggao....
Published date-12/01/2020
PersonRe-Identification
Triplet loss with batch hard mining (TriHard loss) is an important variation of triplet loss inspired by the idea that hard triplets improve the performance of metric leaning networks. However, …
Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning
ShreyasFadnavis, JoshuaBatson, EleftheriosGaryfallidis....
Published date-12/01/2020
Denoising, Self-SupervisedLearning
Diffusion-weighted magnetic resonance imaging (DWI) is the only non-invasive method for quantifying microstructure and reconstructing white-matter pathways in the living human brain. Fluctuations from multiple sources create significant noise in …