Home /

Research

Showing 841 - 846 / 897

Comparison of pharmacist evaluation of medication orders with predictions of a machine learning model


Authors:  Sophie-CamilleHogue, FloraChen, GenevièveBrassard....
Published date-11/03/2020

Abstract: The objective of this work was to assess the clinical performance of an unsupervised machine learning model aimed at identifying unusual medication orders and pharmacological profiles. We conducted a prospective …

CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search


Authors:  ChenyanXiong, ZhenghaoLiu, SiSun....
Published date-11/03/2020
Tasks:  DomainAdaptation, Few-ShotLearning, InformationRetrieval

Abstract: Neural rankers based on deep pretrained language models (LMs) have been shown to improve many information retrieval benchmarks. However, these methods are affected by their the correlation between pretraining domain …

Generalization to New Actions in Reinforcement Learning


Authors:  AyushJain, AndrewSzot, JosephJ.Lim....
Published date-11/03/2020

Abstract: A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes …

Brain Predictability toolbox: a Python library for neuroimaging based machine learning


Authors:  SageHahn, DekangYuan, WesleyThompson....
Published date-11/03/2020

Abstract: Summary Brain Predictability toolbox (BPt) represents a unified framework of machine learning (ML) tools designed to work with both tabulated data (in particular brain, psychiatric, behavioral, and physiological variables) and …

VEGA: Towards an End-to-End Configurable AutoML Pipeline


Authors:  BochaoWang, HangXu, JiajinZhang....
Published date-11/03/2020
Tasks:  AutoML, DataAugmentation, HyperparameterOptimization, ModelCompression, NeuralArchitectureSearch

Abstract: Automated Machine Learning (AutoML) is an important industrial solution for automatic discovery and deployment of the machine learning models. However, designing an integrated AutoML system faces four great challenges of …

Improved unsupervised physics-informed deep learning for intravoxel-incoherent motion modeling and evaluation in pancreatic cancer patients


Authors:  MishaP.T.Kaandorp, SebastianoBarbieri, RemyKlaassen....
Published date-11/03/2020

Abstract: ${\bf Purpose}$: Earlier work showed that IVIM-NET$_{orig}$, an unsupervised physics-informed deep neural network, was faster and more accurate than other state-of-the-art intravoxel-incoherent motion (IVIM) fitting approaches to DWI. This study …

Filter by

Categories

Tags