Filters








567 Hits in 2.9 sec

Liquid Splash Modeling with Neural Networks [article]

Kiwon Um, Xiangyu Hu, Nils Thuerey
2018 arXiv   pre-print
This paper proposes a new data-driven approach to model detailed splashes for liquid simulations with neural networks.  ...  We use neural networks to model the regression of splash formation using a classifier together with a velocity modifier. For the velocity modification, we employ a heteroscedastic model.  ...  We realize our model using machine learning techniques with neural networks (NNs) and integrate the model into the fluidimplicit-particle (FLIP) algorithm [ZB05] .  ... 
arXiv:1704.04456v2 fatcat:qzsah4z57jadvavhwsz62bn5mq

Delayed Synapses: An LSM Model for Studying Aspects of Temporal Context in Memory [chapter]

Predrag Jakimovski, Hedda R. Schmidtke
2011 Lecture Notes in Computer Science  
We extended the liquid state machine model with time-delayed connections from liquid neurons to the readout unit to better capture context phenomena.  ...  Spiking neural networks are promising candidates for representing aspects of cognitive context in human memory.  ...  A liquid state machine consists of a spiking neural network (SNN) with a readout unit implemented by sigmoid neural networks.  ... 
doi:10.1007/978-3-642-24279-3_16 fatcat:ss74dlrh5vh3pntn5xfmhwhwje

Modeling human intuitions about liquid flow with particle-based simulation

Christopher J. Bates, Ilker Yildirim, Joshua B. Tenenbaum, Peter Battaglia, Jean Daunizeau
2019 PLoS Computational Biology  
based on simple heuristics and deep neural networks.  ...  Humans can easily describe, imagine, and, crucially, predict a wide variety of behaviors of liquids-splashing, squirting, gushing, sloshing, soaking, dripping, draining, trickling, pooling, and pouring-despite  ...  In addition, [30] 's recent "interaction networks" and [31] 's "neural physics engine" models introduce neural networks which operate on objects and relations, and can learn very accurate quantitative  ... 
doi:10.1371/journal.pcbi.1007210 pmid:31329579 pmcid:PMC6675131 fatcat:wpqajqthlne73d4lncwddrihyi

The Application of Liquid State Machines in Robot Path Planning

Yanduo Zhang, Kun Wang
2009 Journal of Computers  
Index Terms -Liquid state machines; spiking neural networks; Parallel Delta Rule; path planning  ...  This paper discusses the Liquid state machines and does some researches on spiking neural network and Parallel Delta Rule, using them to solve the robot path planning optimization problems, at the same  ...  the neural network model shown inFigure 4.  ... 
doi:10.4304/jcp.4.11.1182-1186 fatcat:czt7isowxzfkdixdqoq6czlo3a

Modeling human intuitions about liquid flow with particle-based simulation [article]

Christopher J. Bates and Ilker Yildirim and Joshua B. Tenenbaum and Peter Battaglia
2018 arXiv   pre-print
based on simple heuristics and deep neural networks.  ...  Humans can easily describe, imagine, and, crucially, predict a wide variety of behaviors of liquids--splashing, squirting, gushing, sloshing, soaking, dripping, draining, trickling, pooling, and pouring  ...  In addition, [28] 's recent "interaction networks" and [29] 's "neural physics engine" models introduce neural networks which operate on objects and relations, and can learn very accurate quantitative  ... 
arXiv:1809.01524v1 fatcat:cuqic2zif5cdvcsmegshz5komq

Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids [article]

Bruno Roy, Pierre Poulin, Eric Paquette
2021 arXiv   pre-print
We present a novel up-resing technique for generating high-resolution liquids based on scene flow estimation using deep neural networks.  ...  The proposed network leverages neighborhood contributions to encode inherent liquid properties throughout convolutions.  ...  As we focus on neural networks (NN) to enrich the liquid surface, we will not compare our work with procedural methods.  ... 
arXiv:2106.05143v1 fatcat:yzb76xpbrrbstnyi6c7nwqnvby

Generating Liquid Simulations with Deformation-aware Neural Networks [article]

Lukas Prantl, Boris Bonev, Nils Thuerey
2019 arXiv   pre-print
We propose a novel approach for deformation-aware neural networks that learn the weighting and synthesis of dense volumetric deformation fields.  ...  Our algorithm captures these complex phenomena in two stages: a first neural network computes a weighting function for a set of pre-computed deformations, while a second network directly generates a deformation  ...  Once again, we model this function with a neural network, effectively giving the network more expressive capabilities to directly influence the final deformed surface.  ... 
arXiv:1704.07854v4 fatcat:benfmgsv6rf4lclrvceesp4py4

Visual perception of liquids: Insights from deep neural networks

Jan Jaap R. van Assen, Shin'ya Nishida, Roland W. Fleming, Daniele Marinazzo
2020 PLoS Computational Biology  
We trained a DNN to estimate the viscosity of liquids using 100.000 simulations depicting liquids with sixteen different viscosities interacting in ten different scenes (stirring, pouring, splashing, etc  ...  In recent years, artificial Deep Neural Networks (DNNs) have yielded breakthroughs in challenging real-world vision tasks.  ...  Acknowledgments We thank Peter Battaglia for invaluable discussions and help getting started with deep learning and Next Limit for providing support during the stimuli generation process.  ... 
doi:10.1371/journal.pcbi.1008018 pmid:32813688 fatcat:4ogmq7ytrraotcgmsbvmx7626a

Visual perception of liquids: insights from deep neural networks

Jan Jaap R Van Assen, Shin'ya Nishida, Roland W Fleming
2019 Journal of Vision  
We trained a DNN to estimate the viscosity of liquids using 100.000 simulations depicting liquids with sixteen different viscosities interacting in ten different scenes (stirring, pouring, splashing, etc  ...  PLOS COMPUTATIONAL BIOLOGY Visual perception of liquids: Insights from deep neural networks PLOS Computational Biology | https://doi.  ...  Acknowledgments We thank Peter Battaglia for invaluable discussions and help getting started with deep learning and Next Limit for providing support during the stimuli generation process.  ... 
doi:10.1167/19.10.242b fatcat:ny7lnqkmbzfalcntv7u3foeug4

NeuralDrop: DNN-based Simulation of Small-Scale Liquid Flows on Solids [article]

Rajaditya Mukherjee, Qingyang Li, Zhili Chen, Shicheng Chu, Huamin Wang
2018 arXiv   pre-print
In this paper, we propose to simulate the dynamics of new liquid drops from captured real-world liquid flow data, using deep neural networks.  ...  We then convert raw data into compact data for training neural networks, in which liquid drops are represented by their contact fronts in a Lagrangian form.  ...  Bonev and colleagues [2017] proposed to predict surface deformation in water simulation by neural networks and soon Um and collaborators [2017] used it for modeling water splashes.  ... 
arXiv:1811.02517v1 fatcat:h4jjugkc5jbl3becrvrsasulhm

Visual Closed-Loop Control for Pouring Liquids [article]

Connor Schenck, Dieter Fox
2017 arXiv   pre-print
We propose both a model-based and a model-free method utilizing deep learning for estimating the volume of liquid in a container.  ...  We combine this with a simple PID controller to pour specific amounts of liquid, and show that the robot is able to achieve an average 38ml deviation from the target amount.  ...  method replaces the object pose inference of the model-based method with a neural network.  ... 
arXiv:1610.02610v3 fatcat:26yvlkmchrehphaj2not4i5foa

Application of Optimized Neural Network Models for Prediction of Nuclear Magnetic Resonance Parameters in Carbonate Reservoir Rocks

Javad Ghiasi-Freez, Amir Hatampour, Payam Parvasi
2015 International Journal of Intelligent Systems and Applications  
Neural network models are powerful tools for extracting the underlying dependency of a set of input/output data. However, the mentioned tools are in danger of sticking in local minima.  ...  This strategy was capable of significantly improving the accuracy of a neural network by optimizing network parameters such as weights and biases.  ...  Biologists believe that this fact can be possible by splashing special liquid, called pheromones, in their path.  ... 
doi:10.5815/ijisa.2015.06.02 fatcat:6hmw7jcm6jdztfkwfqki2eq2we

Endpoint Prediction of BOF Steelmaking based on BP Neural Network Combined with Improved PSO

W. Li, Q.M. Wang, X.S. Wang, H. Wang
2016 Chemical Engineering Transactions  
More specifically, a back propagation (BP) neural network is employed to estimate the endpoint carbon content and the endpoint temperature of BOF, and an improved particle swarm optimization (PSO) algorithm  ...  is proposed to optimize the prediction model for improving the accuracy of the endpoint prediction.  ...  At present, the mechanism model, statistical model, and artificial neural network model are common static models for BOF steelmaking endpoint control and prediction (Wang et al. 2005) .  ... 
doi:10.3303/cet1651080 doaj:c405883ed97841208cb5f0b5bfce374e fatcat:7j2a42omizeeraz4xj64g7kxay

Deep Fluids: A Generative Network for Parameterized Fluid Simulations [article]

Byungsoo Kim, Vinicius C. Azevedo, Nils Thuerey, Theodore Kim, Markus Gross, Barbara Solenthaler
2019 arXiv   pre-print
A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields.  ...  In addition, we demonstrate that we can handle complex parameterizations in reduced spaces, and advance simulations in time by integrating in the latent space with a second network.  ...  We demonstrate that our approach can also handle splashing liquids.  ... 
arXiv:1806.02071v2 fatcat:gy64u5helrbjrlcwjyk3r44c3e

Invariant representations of mass in the human brain

Sarah Schwettmann, Joshua B Tenenbaum, Nancy Kanwisher
2019 eLife  
An intuitive understanding of physical objects and events is critical for successfully interacting with the world.  ...  To investigate, we scanned participants with fMRI while they viewed videos of objects interacting in scenarios indicating their mass.  ...  These models may make use of deep neural networks, but also 42 contain additional structured information about the world.  ... 
doi:10.7554/elife.46619 pmid:31845887 pmcid:PMC7007217 fatcat:gwnglu2u7jhqxh4fhl5sdkl7z4
« Previous Showing results 1 — 15 out of 567 results