313,194 Hits in 3.2 sec

Deep learning-based pupil model predicts time and spectral dependent light responses

Babak Zandi, Tran Quoc Khanh
2021 Scientific Reports  
Neither the temporal receptor-weighting nor the spectral-dependent adaptation behaviour of the afferent pupil control path is mapped in such functions.  ...  State of the art pupil models rested in estimating a static diameter at the equilibrium-state for spectra along the Planckian locus.  ...  Acknowledgements Calculations on the Lichtenberg high-performance computer of the Technical University of Darmstadt were conducted for this research.  ... 
doi:10.1038/s41598-020-79908-5 pmid:33436693 fatcat:r74efwdi4bcbrj5jbbtxqrgyou

Managing Distributed Adaptation of Mobile Applications [chapter]

Mourad Alia, Svein Hallsteinsen, Nearchos Paspallis, Frank Eliassen
2007 Lecture Notes in Computer Science  
The network management facilities are provided by the the MobileIP network component tailored for mobile mobile in IP networks.  ...  The context manager is responsible for the management of the pool of context listeners, including resource listeners, and for delegating these changes to the adaptation manager. Network management.  ...  The adaptation reasoning relies on the use of utility functions allowing the computation of the utility for the user of an application variant given the current user needs and available computing and communication  ... 
doi:10.1007/978-3-540-72883-2_8 fatcat:h7kdvu2pjnabhidoriu3ozg7fm

Adaptive Dual Network Design for a Class of SIMO Systems with Nonlinear Time-variant Uncertainties

Bo LIU, Hai-Bo HE, Sheng CHEN
2010 Acta Automatica Sinica  
A novel adaptive dual network design consisting of a rough adjustment network (RAN) and a fine adjustment network (FAN) is proposed to eliminate the unknown time-variant uncertainties of servo system.  ...  Simulation results and comparative study of this method with those of existing approaches demonstrate the effectiveness of the proposed adaptive dual network design for position tracking.  ...  In this paper, we propose a dual network design approach including a Fourier series based sliding mode adaptive control (FSSMAC) network for rough adjustment and an adaptive prediction critic network for  ... 
doi:10.1016/s1874-1029(09)60023-9 fatcat:gq25scww2rg2haw7zk42dqvqre

Phenotype Heritability in holobionts: An Evolutionary Model [article]

Saul Huitzil, Santiago Sandoval-Motta, Alejandro Frank, Maximino Aldana
2020 bioRxiv   pre-print
Here we test this hypothesis by studying an evolutionary model based on gene regulatory networks.  ...  However, genetic studies have been unable to identify the genomic signatures responsible for such heritability, as identifying the genetic variants that make a population prone to a given disease is not  ...  Fig. 4 4 (a) Plot of the normalized effect / 0 of the variants as a function of the variant index , with 1 ≤ ≤ 200, for a network with = 50 and connectivity = 2.  ... 
doi:10.1101/2020.05.05.079137 fatcat:cj4mai4bvbhqbmhysfylcb3usq

A Rendezvous of Content Adaptable Service and Product Line Modeling [chapter]

Seo Jeong Lee, Soo Dong Kim
2005 Lecture Notes in Computer Science  
In this paper, we propose a service decision modeling technique for content adaptable applications in ubiquitous environment.  ...  Modeling with software features and product line concepts may support for making service decision strategy.  ...  The Content Adaptable Service Decision Process This chapter suggests a process model for content adaptable service.  ... 
doi:10.1007/11497455_8 fatcat:lggve5lfvndqtn7pngpcczovma

Neural Networks for Modal and Virtual Learning [chapter]

Dominic Palmer-Brown
2009 IFIP Advances in Information and Communication Technology  
or guided by performance feedback (reinforcement) and an adaptive function Neural Network (ADFUNN) in which adaption applies simultaneously to both the weights and the individual neuron activation functions  ...  from non-stationary input data, or time variant learning oblectives, where the optimal mode is a function of time.  ...  or guided by performance feedback (reinforcement) and an adaptive function Neural Network (ADFUNN) in which adaption applies simultaneously to both the weights and the individual neuron activation functions  ... 
doi:10.1007/978-1-4419-0221-4_2 fatcat:g5ckb4jlurff7hgw7vfirq2itm

SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions [article]

A. Ali Heydari, Craig A. Thompson, Asif Mehmood
2019 arXiv   pre-print
However, existing frameworks of adaptive loss functions often suffer from slow convergence and poor choice of weights for the loss components.  ...  Adaptive loss function formulation is an active area of research and has gained a great deal of popularity in recent years, following the success of deep learning.  ...  We would like to thank Fred Garber, Olga Mendoza-Shrock, Jamison Moody, Oliver Nina, Alexis Ronnebaum and Suzanne Sindi for their feedback and support.  ... 
arXiv:1912.12355v1 fatcat:nqbttgpb7zbedoicowr3hkol5e

Using a neural network for estimating plant gradients in real-time optimization with modifier adaptation

José Matias, Johannes Jäschke
2019 IFAC-PapersOnLine  
This work proposes a method for estimating plant gradients based on neural networks (radial basis function network -RBFN).  ...  This work proposes a method for estimating plant gradients based on neural networks (radial basis function network -RBFN).  ...  Dinesh Krishnamoorthy for providing the process models used in this work. The authors acknowledge Financial Support from the Norwegian research council /Intpart, SUBPRO  ... 
doi:10.1016/j.ifacol.2019.06.161 fatcat:mvyyb766fndgzi7fptrsiidmpm

A Spiking Neuron and Population Model based on the Growth Transform Dynamical System [article]

Ahana Gangopadhyay, Darshit Mehta, Shantanu Chakrabartty
2019 bioRxiv   pre-print
One such variant described in this paper is a network that adapts itself according to the global dynamics to encode the steady-state solution with a reduced number of spikes.  ...  The model allows integration and control of two different types of dynamics: (a) sub-threshold dynamics that determines the fixed-point solution of an underlying network objective or energy functional;  ...  We then introduce a form of the energy function for a non-spiking variant of a neuron model based on this dynamical system, and extend it to a spiking variant that stochastically minimizes the network  ... 
doi:10.1101/523944 fatcat:kxqrmxchezgebmchquecggjjgm

yMap: An automated method to map yeast variants to protein modifications and functional regions

Ahmed Arslan, Vera van Noort
2016 Bioinformatics  
However, for model organisms such as yeast such tools are lacking, specifically to predict the effect of protein sequence altering variants on the protein level.  ...  For the human genome, several tools are available to predict the impact of these variants on gene and protein functions.  ...  Together, this suggests adaption may be achieved through rewiring of the signaling network.  ... 
doi:10.1093/bioinformatics/btw658 pmid:27797766 pmcid:PMC5408805 fatcat:dyttnruvajg7zakydwrs7qxufa

Hybridised Loss Functions for Improved Neural Network Generalisation [chapter]

Matthew C. Dickson, Anna S. Bosman, Katherine M. Malan
2022 Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering  
Loss functions play an important role in the training of artificial neural networks (ANNs), and can affect the generalisation ability of the ANN model, among other properties.  ...  not be significantly different than the best loss function tested for all problems considered.  ...  Introduction Loss functions in artificial neural networks (ANNs) are used to quantify the error produced by the model on a given dataset.  ... 
doi:10.1007/978-3-030-93314-2_11 fatcat:iyyuuxvyoff4pdxhatlhfyutvi

Multi-variant COVID-19 model with heterogeneous transmission rates using deep neural networks [article]

K.D. Olumoyin, A.Q.M. Khaliq, K.M. Furati
2022 arXiv   pre-print
A Deep neural network is utilized and a deep learning algorithm is developed to learn the time-varying heterogeneous transmission rates for each variant.  ...  Short-term forecasting of daily cases is demonstrated using long short term memory neural network and an adaptive neuro-fuzzy inference system.  ...  Neural Network (EINN) and we forecast using an adaptive neuro-fuzzy system (ANFIS), which we called the EINN-ANFIS model.  ... 
arXiv:2205.06834v1 fatcat:fhwchw55e5c47ig4phwmck24na

Putting together QoS and security in autonomic pervasive systems

Mourad Alia, Marc Lacoste, Ruan He, Frank Eliassen
2010 Proceedings of the 6th ACM workshop on QoS and security for wireless and mobile networks - Q2SWinet '10  
This paper presents an adaptation model based on selection of component compositions enabling to capture dynamic and fine-grained trade-offs between both QoS and security in those systems.  ...  We illustrate through a case study of a typical Beyond 3G adaptive multimedia streaming service how the model may be applied to find the right balance between different QoS and security dimensions.  ...  QoS adaptation planning on 1000 variants yields adaptation times around 1 s which may be acceptable for an end user. However, this may not be the case when adapting security mechanisms.  ... 
doi:10.1145/1868630.1868634 dblp:conf/mswim/AliaLHE10 fatcat:uagzadrh4bgkxalnxpuos2hsja

DANE: Domain Adaptive Network Embedding [article]

Yizhou Zhang, Guojie Song, Lun Du, Shuwen Yang, Yilun Jin
2019 arXiv   pre-print
Hence, it is important to design a network embedding algorithm that supports downstream model transferring on different networks, known as domain adaptation.  ...  However, as previous methods usually focus on learning embeddings for a single network, they can not learn representations transferable on multiple networks.  ...  Domain adaptation on networks aims to train a machine learning model M for a downstream task by minimizing its loss function on G src and ensure that M can also have good performance when we transfer it  ... 
arXiv:1906.00684v2 fatcat:5tmdx55hvjg2to7s6ie44ef454

Hosting and Using Services with QoS Guarantee in Self-adaptive Service Systems [chapter]

Shanshan Jiang, Svein Hallsteinsen, Paolo Barone, Alessandro Mamelli, Stephan Mehlhase, Ulrich Scholz
2010 Lecture Notes in Computer Science  
In this paper we propose a solution based on the integration of an SLA mechanism into a compositional adaptation planning framework and describe a simple yet powerful implementation targeted for resource  ...  To this end, service level negotiation and agreements (SLA) are important to ensure coordinated end to end adaptation.  ...  Both information can be included in the utility function for adaptation reasoning.  ... 
doi:10.1007/978-3-642-13645-0_2 fatcat:fij3eyt5zbgu3mouroytgk2gwu
« Previous Showing results 1 — 15 out of 313,194 results