Results 51 to 60 of about 539,870 (246)

Weakly-Supervised Bayesian Learning of a CCG Supertagger

, 2018
We present a Bayesian formulation for weakly-supervised learning of a Combinatory Categorial Grammar (CCG) supertagger with an HMM. We assume supervision in the form of a tag dictionary, and our prior encourages the use of crosslinguistically common ...
Noah A. Smith (663492), Dan Garrette (5362844), Jason Baldridge (5361860), Chris Dyer (5361836)   +3 more
core   +1 more source

Benchmarking weakly-supervised deep learning pipelines for whole slide classification in computational pathology. [PDF]

, 2022
Artificial intelligence (AI) can extract visual information from histopathological slides and yield biological insight and clinical biomarkers. Whole slide images are cut into thousands of tiles and classification problems are often weakly-supervised ...
Hoffmeister, Michael, Lu, Ming Y, Khader, Firas, Grabsch, Heike Irmgard, Ghaffari Laleh, Narmin, Dislich, Bastian, Boor, Peter, Brenner, Hermann, Brinker, Titus J, Saldanha, Oliver Lester, Gaisa, Nadine T, Loeffler, Chiara Maria Lavinia, Alwers, Elizabeth, Chang-Claude, Jenny, Mahmood, Faisal, Buelow, Roman D, Muti, Hannah Sophie, Schulz, Volkmar, Echle, Amelie, Trautwein, Christian, Truhn, Daniel, Langer, Rupert, Kather, Jakob Nikolas   +22 more
core   +2 more sources

A novel quinazolinone insulin receptor inhibitor and its synergy with an EGFR inhibitor in glucose‐driven glioblastoma

Molecular Oncology, EarlyView.
The novel styrylquinazolinone‐based molecule W1B effectively suppresses glioblastoma by inhibiting IGF1R and EGFR. In high‐glucose microenvironments driving tumor resistance, W1B acts synergistically with the EGFR inhibitor dacomitinib. This combination safely blocks compensatory survival signaling in zebrafish xenograft models. Showcasing promising in
Patryk Rurka, Wioleta Cieślik, Wojciech Płaziński, Katarzyna Stępnik, Anna Boguszewska‐Czubara, Elżbieta Kot, Robert Musioł, Mateusz Jasica, Anna Mrozek‐Wilczkiewicz, Katarzyna Malarz   +9 more
wiley   +1 more source

Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss

Transactions of the Association for Computational Linguistics, 2019
In many machine learning scenarios, supervision by gold labels is not available and conse quently neural models cannot be trained directly by maximum likelihood estimation.
Jehl, Laura, Lawrence, Carolin, Riezler, Stefan   +2 more
doaj   +1 more source

Weakly Supervised Human Fixations Prediction

, 2016
Automatically predicting human eye fixations is a useful technique that can facilitate many multimedia applications, e.g., image retrieval, action recognition, and photo retargeting. Conventional approaches are frustrated by two drawbacks.
Zhang, Luming, Nie, Liqiang, Li, X, Li, Xuelong, Xia, Yingjie, Xia, YJ, Zhang, L, Yang, Y, Xia, Y, Nie, L, Yang, Yi   +10 more
core   +1 more source

In vitro and in silico modelling of ROS1‐positive non‐small cell lung cancer reveals fusion‐dependent tyrosine kinase inhibitor responses

Molecular Oncology, EarlyView.
Drug resistance limits treatment success in a subset of lung cancers driven by ROS1 gene alterations. Using patient‐derived cells and computer simulations, we studied three key mutations and how they affect five targeted drugs. The mutations reduced drug effectiveness in different ways by altering protein structure and behavior.
Farhan Ul Haq, Marc Terrones, Felicia Rodrigues Fortes, Anne Schepers, Alessia Denis, Christophe Deben, Ken Op de Beeck, Guy Van Camp, Geert Vandeweyer   +8 more
wiley   +1 more source

Weakly supervised spatial–temporal attention network driven by tracking and consistency loss for action detection

EURASIP Journal on Image and Video Processing, 2022
This study proposes a novel network model for video action tube detection. This model is based on a location-interactive weakly supervised spatial–temporal attention mechanism driven by multiple loss functions.
Jinlei Zhu, Houjin Chen, Pan Pan, Jia Sun   +3 more
doaj   +1 more source

Learning Uncertainty-Aware Label Transition for Weakly Supervised Solar Panel Mapping with Aerial Images

, 2022
Weakly supervised solar panel mapping has shown its advantages in automatically detecting solar panels from remote sensing images with low annotation costs.
Zhou, Jun, Zhang, Jue, Hu, Jiankun, Jia, Xiuping   +3 more
core   +1 more source

Intrapatient tumour heterogeneity and clonal evolution in an autopsy study of metastatic salivary gland cancer

Molecular Oncology, EarlyView.
Tumour heterogeneity and clonal evolution of metastatic salivary gland cancer were evaluated in two patients with adenoid carcinoma and one patient with myoepithelial carcinoma. Radiology‐guided autopsy enabled multi‐region sampling (total samples n = 149), followed by whole‐genome sequencing and phylogenetic reconstruction (17 tumour samples, 4–7 per ...
Gerben Lassche, Niels J. van Ruitenbeek, Charlotte Adang, Luke O'Gorman, Pui Yuen Lee, Willemijn M. Klein, Adriana C. H. van Engen‐van Grunsven, Jack A. Schalken, Sander Bervoets, Gerald W. Verhaegh, Carla M. L. van Herpen   +10 more
wiley   +1 more source

Partial FAK suppression promotes tumor growth, an effect reversed by macrophage p110δ PI3K inactivation

Molecular Oncology, EarlyView.
Partial inhibition of focal adhesion kinase (FAK) can paradoxically promote tumor growth, rather than simply producing a weaker antitumor effect than that observed with strong FAK suppression. In breast cancer and melanoma models, targeting p110δ PI3K, particularly in macrophages, counteracted these tumor‐promoting effects, highlighting the importance ...
Lydia Xenou, Niki Tzenaki, Anna Tsapara, Maria Tzardi, Evangelia A. Papakonstanti   +4 more
wiley   +1 more source