Results 71 to 80 of about 806,463 (274)

Learning to Balance Local Losses via Meta-Learning

IEEE Access, 2021
The standard training for deep neural networks relies on a global and fixed loss function. For more effective training, dynamic loss functions have been recently proposed.
Seungdong Yoa, Minkyu Jeon, Youngjin Oh, Hyunwoo J. Kim   +3 more
doaj   +1 more source

Organ‐specific redox imbalances in spinal muscular atrophy mice are partially rescued by SMN antisense oligonucleotides

FEBS Letters, EarlyView.
We identified a systemic, progressive loss of protein S‐glutathionylation—detected by nonreducing western blotting—alongside dysregulation of glutathione‐cycle enzymes in both neuronal and peripheral tissues of Taiwanese SMA mice. These alterations were partially rescued by SMN antisense oligonucleotide therapy, revealing persistent redox imbalance as ...
Sofia Vrettou, Brunhilde Wirth
wiley   +1 more source

Cross-layer transmission realized by light-emitting memristor for constructing ultra-deep neural network with transfer learning ability

Nature Communications
Deep neural networks have revolutionized several domains, including autonomous driving, cancer detection, and drug design, and are the foundation for massive artificial intelligence models.
Zhenjia Chen, Zhenyuan Lin, Ji Yang, Cong Chen, Di Liu, Liuting Shan, Yuanyuan Hu, Tailiang Guo, Huipeng Chen   +8 more
doaj   +1 more source

Patient‐specific pharmacogenomics demonstrates xCT as predictive therapeutic target in colon cancer with possible implications in tumor connectivity

Molecular Oncology, EarlyView.
This study integrates transcriptomic profiling of matched tumor and healthy tissues from 32 colorectal cancer patients with functional validation in patient‐derived organoids, revealing dysregulated metabolic programs driven by overexpressed xCT (SLC7A11) and SLC3A2, identifying an oncogenic cystine/glutamate transporter signature linked to ...
Marco Strecker, Keren Zohar, Martin Böttcher, Thomas Wartmann, Henry Freudenstein, Maximilian Doelling, Mihailo Andric, Wenjie Shi, Or Kakhlon, Katrin Hippe, Beatrix Jahnke, Dimitrios Mougiakakos, Franziska Baenke, Daniel Stange, Roland S. Croner, Michal Linial, Ulf D. Kahlert   +16 more
wiley   +1 more source

Optimized Deep Convolutional Neural Networks for Identification of Macular Diseases from Optical Coherence Tomography Images

Algorithms, 2019
Finetuning pre-trained deep neural networks (DNN) delicately designed for large-scale natural images may not be suitable for medical images due to the intrinsic difference between the datasets.
Qingge Ji, Jie Huang, Wenjie He, Yankui Sun   +3 more
doaj   +1 more source

Non-attracting Regions of Local Minima in Deep and Wide Neural Networks

, 2020
Understanding the loss surface of neural networks is essential for the design of models with predictable performance and their success in applications.
Petzka, Henning, Sminchisescu, Cristian
core  

The neural crest‐associated gene ERRFI1 is involved in melanoma progression and resistance toward targeted therapy

Molecular Oncology, EarlyView.
ERRFI1, a neural crest (NC)‐associated gene, was upregulated in melanoma and negatively correlated with the expression of melanocytic differentiation markers and the susceptibility of melanoma cells toward BRAF inhibitors (BRAFi). Knocking down ERRFI1 significantly increased the sensitivity of melanoma cells to BRAFi.
Nina Wang, Qian Sun, Daniel Novak, Lei Zhu, Juliane Poelchen, Tamara Steinfass, Yiman Wang, Viktor Umansky, Jochen Utikal   +8 more
wiley   +1 more source

Two-Stage Approach to Image Classification by Deep Neural Networks

EPJ Web of Conferences, 2018
The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying.
Ososkov Gennady, Goncharov Pavel
doaj   +1 more source

Spiking Neural Networks and Their Applications: A Review

Brain Sciences, 2022
The past decade has witnessed the great success of deep neural networks in various domains. However, deep neural networks are very resource-intensive in terms of energy consumption, data requirements, and high computational costs.
Kashu Yamazaki, Viet-Khoa Vo-Ho, Darshan Bulsara, Ngan Le   +3 more
doaj   +1 more source

Liquid biopsy epigenetics: establishing a molecular profile based on cell‐free DNA

Molecular Oncology, EarlyView.
Cell‐free DNA (cfDNA) fragments in plasma from cancer patients carry epigenetic signatures reflecting their cells of origin. These epigenetic features include DNA methylation, nucleosome modifications, and variations in fragmentation. This review describes the biological properties of each feature and explores optimal strategies for harnessing cfDNA ...
Christoffer Trier Maansson, Anders Lade Nielsen, Boe Sandahl Sorensen   +2 more
wiley   +1 more source