Results 41 to 50 of about 482,653 (299)
Deep transfer network of heterogeneous domain feature in machine translation
High-Confidence Computing, 2022 In order to address the shortcoming of feature representation limitation in machine translation(MT) system, this paper presents a feature transfer method in MT.
Yupeng Liu, Yanan Zhang, Xiaochen Zhang
doaj +1 more source
Transfer learning example: DenseNet201 pre-trained feature extraction layers.
, 2023 Transfer learning example: DenseNet201 pre-trained feature extraction layers.
Ahmad Salah (9034673) +3 more
core +1 more source
Transfer with Model Features in Reinforcement Learning
CoRR, 2018 A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring knowledge between tasks with shared transition dynamics. This paper presents Model Features: a feature representation that
Lucas Lehnert, Michael L. Littman
openaire +2 more sources
Pediatric Blood &Cancer, EarlyView.ABSTRACT Background Pediatric sarcomas are a heterogeneous group of tumors that contribute disproportionately to cancer mortality in children. Although congenital anomalies are among the strongest known risk factors for childhood cancer, the risk of specific sarcoma subtypes among affected individuals has not yet been thoroughly evaluated. Procedure We
Russ Wolters +17 more
wiley +1 more source
Good Practice in CNN Feature Transfer
CoRR, 2016 9 pages.
Liang Zheng 0001 +4 more
openaire +2 more sources
Arbitrary Style Transfer with Deep Feature Reshuffle [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018 This paper introduces a novel method by reshuffling deep features (i.e., permuting the spacial locations of a feature map) of the style image for arbitrary style transfer. We theoretically prove that our new style loss based on reshuffle connects both global and local style losses respectively used by most parametric and non-parametric neural style ...
Shuyang Gu +3 more
openaire +2 more sources
Supporting Survivor‐Centered Care Through Digital Health Integration
Pediatric Blood &Cancer, EarlyView.ABSTRACT Survivors of childhood cancer face barriers to receiving guideline‐based, long‐term follow‐up care. Two digital tools, Passport for Care (PFC) and Cancer SurvivorLink (SurvivorLink), address complementary gaps by enabling tailored survivorship care plan (SCP) generation, updating, storage, and sharing.
Jordan G. Marchak +15 more
wiley +1 more source
Dual-Space Transfer Learning Based on an Indirect Mutual Promotion Strategy
International Journal of Computational Intelligence Systems, 2022 Transfer learning is designed to leverage knowledge in the source domain with labels to help build classification models in the target domain where labels are scarce or even unavailable. Previous studies have shown that high-level concepts extracted from
Teng Cui +3 more
doaj +1 more source
Therapeutic Apheresis and Dialysis, EarlyView.ABSTRACT Objective To compare the efficacy and safety of roxarestat versus recombinant human erythropoietin (rhEPO) in the management of renal anemia in patients undergoing maintenance hemodialysis. Methods This was a prospective, open‐label, randomized controlled trial.
Lingling Chen, Junjie Zhu, Qiaonan Ge
wiley +1 more source
Successor Features for Transfer in Reinforcement Learning
, 2016 Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes between tasks but the environment's dynamics remain the same.
André Barreto 0001 +6 more
openaire +3 more sources