Results 91 to 100 of about 296,489 (278)
Molecular Oncology, EarlyView.Beyond its role in immune evasion, this study identified that CD47 drives tumor‐intrinsic signaling in non‐small cell lung cancer (NSCLC). Transcriptomic profiling and functional studies revealed that CD47 regulates cell adhesion, migration, and metastasis through an ERK–EMT signaling axis.
Asa P.Y. Lau +8 more
wiley +1 more source
Adaptive spatiotemporal neural networks through complementary hybridization
Nature CommunicationsProcessing spatiotemporal data sources with both high spatial dimension and rich temporal information is a ubiquitous need in machine intelligence. Recurrent neural networks in the machine learning domain and bio-inspired spiking neural networks in the ...
Yujie Wu +7 more
doaj +1 more source
Sequence Transduction with Recurrent Neural Networks [PDF]
, 2012 Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to name but a few ...
Graves, Alex
core
Lipschitz Recurrent Neural Networks
, 2020 Published as a conference paper at ICLR ...
N. Benjamin Erichson +4 more
openaire +3 more sources
Recurrent Neural Networks as Electrical Networks, a Formalization
, 2023 Since the 1980s, and particularly with the Hopfield model, recurrent neural networks or RNN became a topic of great interest. The first works of neural networks consisted of simple systems of a few neurons that were commonly simulated through analogue electronic circuits.
Mariano Caruso, Cecilia Jarne
openaire +2 more sources
Learning compact recurrent neural networks [PDF]
2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016 Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile devices with memory and latency constraints. In this work, we study mechanisms for learning compact RNNs and LSTMs via
Zhiyun Lu +2 more
openaire +2 more sources
NKCC1: A key regulator of glioblastoma progression
Molecular Oncology, EarlyView.Glioblastoma (GBM) progression is driven by disrupted chloride cotransporter homeostasis. NKCC1 is highly expressed in stem‐like, astrocytic, and progenitor cells, correlating with earlier recurrence, while overall survival remains unaffected. NKCC1 serves as a prognostic marker and potential therapeutic target, linking chloride transporter imbalance ...
Anja Thomsen +5 more
wiley +1 more source
Molecular Oncology, EarlyView.Dormant cancer cells can hide in distant organs for years, evading treatment and the immune system. This review highlights how signals from the surrounding tissue and immune environment keep these cells inactive or trigger their reawakening. Understanding these mechanisms may help develop therapies to eliminate or control dormant cells and prevent ...
Kanishka Tiwary +1 more
wiley +1 more source
Sliced Recurrent Neural Networks
CoRR, 2018 12 pages (including references), 2 figures, 3 tables, conference: The 27th International Conference on Computational Linguistics (COLING 2018)
Zeping Yu, Gongshen Liu
openaire +3 more sources
BMI‐1 modulation and trafficking during M phase in diffuse intrinsic pontine glioma
FEBS Open Bio, EarlyView.The schematic illustrates BMI‐1 phosphorylation during M phase, which triggers its translocation from the nucleus to the cytoplasm. In cycling cells, BMI‐1 functions within the PRC1 complex to mediate H2A K119 monoubiquitination. Following PTC596‐induced M phase arrest, phosphorylated BMI‐1 dissociates from PRC1 and is exported to the cytoplasm via its
Banlanjo Umaru +6 more
wiley +1 more source