Results 81 to 90 of about 3,951 (305)

Water quality prediction method based on preferred classification

IET Cyber-Physical Systems, 2020
Water quality monitoring and prediction are important parts of Cyber Physical Systems. Considering the complexity, diversity, and strong non-linearity of water quality data, a single water quality prediction model is difficult to have a significant ...
Liming Sheng, Jian Zhou, Xin Li, Yifan Pan, Linfeng Liu   +4 more
doaj   +1 more source

Fast training of Recurrent Neural Networks by the Recursive Least Squares Method

, 1997
In this work a novel approach to the training of recurrent neural nets is presented. the algorithm exploits the separability of each neuron into its linear and nonlinear part. Each iteration of the learning consists of two steps: first the descent of the
RAPAGNETTA A., G. Orlandi, ORLANDI, Gianni, A. Rapagnetta, PARISI, Raffaele, R. Parisi, E. D. Di Claudio, DI CLAUDIO, Elio   +7 more
core   +1 more source

Dynamic Analysis of Recurrent Neural Networks [PDF]

, 2021
With the advancement in deep learning research, neural networks have become one of the most powerful tools for artificial intelligence tasks. More specifically, recurrent neural networks (RNNs) have achieved state-of-the-art in tasks such as hand-writing
Wang, Han
core  

Acute caffeine treatment protects the developing retina from ischemia‐induced cell death

FEBS Open Bio, EarlyView.
Caffeine reduces cell death in the developing retina under ischemia (OGD). This effect does not involve BDNF upregulation or antioxidant pathways (NRF2/VEGF). Neuroprotection occurs mainly through adenosine A2A receptor antagonism, decreasing glutamate release and excitotoxicity, highlighting caffeine's potential as an acute neuroprotective agent in ...
Amanda Alves Nascimento, Danniel Pereira‐Figueiredo, Gabriella Grossi de Lima Dias, Gabriel Ferreira dos Santos, Mariana Rodrigues Pereira, Rafael Brito, Karin C Calaza   +6 more
wiley   +1 more source

Hybrid load prediction model of 5G base station based on time series decomposition and GRU network with parameter optimization

IET Generation, Transmission & Distribution
To ensure the safe and stable operation of 5G base stations, it is essential to accurately predict their power load. However, current short‐term prediction methods are rarely applied rationally in pertinent circumstances to the features of base station ...
Guoxiang Hua, Yan Sun, Weiwei Li
doaj   +1 more source

Modeling user navigation [PDF]

, 2003
This paper proposes the use of neural networks as a tool for studying navigation within virtual worlds. Results indicate that the network learned to predict the next step for a given trajectory.
Mangina, E., Marian, I., Sas, Corina, O'Hare, G.M.P., Reilly, R.   +4 more
core  

One size does not fit all: An in vitro evaluation of the effects of bezafibrate and medroxyprogesterone acetate on human SH‐SY5Y and U‐87 MG cancer cells

FEBS Open Bio, EarlyView.
Drugs previously repurposed to target blood cancers reduced neuroblastoma and glioblastoma cell growth and viability. However, their levels of anticancer activity were different and their clinical application may be problematic due to side effects at effective doses.
Abhishek Kharawatkar, Francesco Michelangeli, Farhat Latif Khanim, Christopher Martin Bunce, William Eustace Basil Johnson   +4 more
wiley   +1 more source

Stochastic neural networks

Revista Colombiana de Estadística, 1991
Artificial neural networks are brain-like models of parallel computations and cognitive phenomena. We sample some basic results about neural networks as they relate to stochastic and statistical processes.
Garzón Max, Torres Luz Gloria
doaj  

A Connectionist Model of Spatial Knowledge Acquisition in a Virtual Environment [PDF]

, 2003
This paper proposes the use of neural networks as a tool for studying navigation within virtual worlds. Results indicate that network learned to predict the next step for a given trajectory, acquiring also basic spatial knowledge in terms of landmarks ...
Sas, Corina, O'Hare, G.M.P., Reilly, R.
core  

Directed evolution of enzymes at the crossroads of tradition and innovation

FEBS Open Bio, EarlyView.
An iterative cycle of data‐driven enzyme optimization comprising four stages: genetic diversification of a template enzyme, expression of protein variants, high‐throughput evaluation, and machine‐learning‐guided redesign of the next variant library.
Maria Tomkova, Andrej Mirossay, Erik Sedlak   +2 more
wiley   +1 more source