Filters








34,374 Hits in 3.8 sec

Neural Spatio-Temporal Point Processes [article]

Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel
2021 arXiv   pre-print
We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of discrete events that are  ...  Central to our approach is a combination of continuous-time neural networks with two novel neural architectures, i.e., Jump and Attentive Continuous-time Normalizing Flows.  ...  ., spatio-temporal point processes and continuous-time normalizing flows.  ... 
arXiv:2011.04583v3 fatcat:patttdhk5jhn5pqtgoputzwebi

Imitation Learning of Neural Spatio-Temporal Point Processes [article]

Shixiang Zhu, Shuang Li, Zhigang Peng, Yao Xie
2021 arXiv   pre-print
We present a novel Neural Embedding Spatio-Temporal (NEST) point process model for spatio-temporal discrete event data and develop an efficient imitation learning (a type of reinforcement learning) based  ...  Despite the rapid development of one-dimensional temporal point processes for discrete event data, the study of spatial-temporal aspects of such data is relatively scarce.  ...  It remains an open question on extending this type of approach to include the spatio-temporal point processes.  ... 
arXiv:1906.05467v4 fatcat:5hpjnqgadjb5rmsnu7gmdkquzm

Deep Fourier Kernel for Self-Attentive Point Processes [article]

Shixiang Zhu, Minghe Zhang, Ruyi Ding, Yao Xie
2021 arXiv   pre-print
We borrow the idea from the attention mechanism and incorporate it into the point processes' conditional intensity function.  ...  We present a novel attention-based model for discrete event data to capture complex non-linear temporal dependence structures.  ...  Self-attentive hawkes processes. Zhu, S., Li, S., and Xie, Y. (2019) . Interpretable generative neural spatio-temporal point processes. Zhu, S. and Xie, Y. (2019).  ... 
arXiv:2002.07281v5 fatcat:ubmconvmdvgt3knvc3ehbchm7i

Blind separation of spatio-temporal Synfire sources and visualization of neural cliques

Hilit Unger, Yehoshua Y. Zeevi
2006 Neurocomputing  
A dominating paradigm in neuroscience attributes components of perception and behavior to synchronous spatio-temporal activities of subsets of neurons within neural networks -the so-called Synfire chains  ...  Assuming stationarity and, to a first approximation, linearity, we extend the Blind Source Separation (BSS) technique to the spatio-temporal domain, to deal with dynamic signals, and apply it on our analysis  ...  To better understand the concept of cliques in the context of spatio-temporal neural network activity, recall the representation of spatio-temporal data as a cubical data set (Fig. 1) .  ... 
doi:10.1016/j.neucom.2005.12.024 fatcat:nzrwj6ji2nc7hdh52bvdcr2nc4

Bayesian Neural Hawkes Process for Event Uncertainty Prediction [article]

Manisha Dubey, Ragja Palakkadavath, P.K. Srijith
2022 arXiv   pre-print
However, neural point process models lack a good uncertainty quantification capability on predictions.  ...  Therefore, we propose a novel point process model, Bayesian Neural Hawkes process (BNHP) which leverages uncertainty modelling capability of Bayesian models and generalization capability of the neural  ...  ., 2021] has introduced deep spatio-temporal point process where they integrate spatio-temporal point process with deep learning by modeling space-time intensity function as mixture of kernels where intensity  ... 
arXiv:2112.14474v2 fatcat:omhl7crmovcxvnfgsfwjrx3pha

COMPREHENSIVE STUDY OF APPLICATIONS OF SPATIO TEMPORAL DATA MINING IN GIS

Rajat Malik
2018 International Journal of Advanced Research in Computer Science  
In this paper we have discussed the spatio temporal dimension of data mining and its applications in field of Geographical Information Systems.  ...  The process of extraction knowledge led to coining of new term called data mining.  ...  Figure 1knowledge Discovery 1knowledge Process [11] Figure 2Spatio Temporal 2Spatio Datamining Process [12] Figure 3Applicatios Of 3Applicatios Spatio Temporal Data [10] Li et al. have discussed  ... 
doi:10.26483/ijarcs.v9i2.5686 fatcat:rcehwamzzng6rhqccost3upggy

A Spatio-Temporal Spot-Forecasting Framework for Urban Traffic Prediction [article]

Rodrigo de Medrano, José L. Aznarte
2020 arXiv   pre-print
In this work we focus on creating a complex deep neural framework for spatio-temporal traffic forecasting with comparatively very good performance and that shows to be adaptable over several spatio-temporal  ...  Our proposal is based on an interpretable attention-based neural network in which several modules are combined in order to capture key spatio-temporal time series components.  ...  Pointing in this direction, through this work we propose a novel Neural Network called CRANN (from Convo-Recurrent Attentional Neural Network) that is evaluated for several spatio-temporal conditions and  ... 
arXiv:2003.13977v2 fatcat:rtipocx6fzabxgp4xwubzqz5aq

Statistical Deep Learning for Spatial and Spatio-Temporal Data [article]

Christopher K. Wikle, Andrew Zammit-Mangion
2022 arXiv   pre-print
deep Gaussian processes.  ...  Indeed, deep models have also been extensively used by the statistical community to model spatial and spatio-temporal data through, for example, the use of multi-level Bayesian hierarchical models and  ...  More directly though, one can use normalizing flows to model the intensity function of a non-homogeneous (temporal, spatial, or spatio-temporal) Poisson point process.  ... 
arXiv:2206.02218v1 fatcat:jbn4rszdxvcajgp3hsnr5i7bqa

Chaotic Time Series Prediction using Spatio-Temporal RBF Neural Networks [article]

Alishba Sadiq, Muhammad Sohail Ibrahim, Muhammad Usman, Muhammad Zubair, Shujaat Khan
2019 arXiv   pre-print
Herein, we propose an spatio-temporal extension of RBF neural networks for the prediction of chaotic time series.  ...  Spatio-temporal analysis of signal provides more advantages over conventional uni-dimensional approaches by harnessing the information from both the temporal and spatial domains.  ...  However in spatio-temporal processing of signal we also need temporal expansion of signal in kernel space as shown in Fig. 1 .  ... 
arXiv:1908.08389v1 fatcat:pm77mtq2obey7ox3ji27pzlvge

A Novel Framework for Spatio-Temporal Prediction of Climate Data Using Deep Learning [article]

Federico Amato, Fabian Guignard, Sylvain Robert, Mikhail Kanevski
2020 arXiv   pre-print
of continuous spatio-temporal fields measured on a set of irregular points in space is still under-investigated.  ...  Specifically, we show how spatio-temporal processes can be decomposed in terms of a sum of products of temporally referenced basis functions, and of stochastic spatial coefficients which can be spatially  ...  The proposed methodology permits to model non-stationary spatio-temporal processes.  ... 
arXiv:2007.11836v1 fatcat:6yihb3tqhjgurlvhpphg6brjo4

Survey on Research of RNN-Based Spatio-Temporal Sequence Prediction Algorithms

Wei Fang, Yupeng Chen, Qiongying Xue
2021 Journal on Big Data  
in processing Spatio-temporal sequence data.  ...  Finally, it prospects the future development of RNN in the Spatio-temporal sequence prediction algorithm.  ...  Besides, the short-term precipitation forecast relies on Spatio-temporal sequence data, so more and more researches apply the convolutional neural network algorithm that best fits the Spatio-temporal sequence  ... 
doi:10.32604/jbd.2021.016993 fatcat:tu5ctgr5p5em7afjc66wqwq3ya

Emergence of oscillations and spatio-temporal coherence states in a continuum-model of excitatory and inhibitory neurons

Silvio P. Sabatini, Fabio Solari, Luca Secchi
2005 Biosystems (Amsterdam. Print)  
where each point in space corresponds to a neural population [6] .  ...  In this paper, we aimed to model the joint spatio-temporal oscillatory dynamics observed in the visual cortices [1] [9], through the behaviour of a field oscillatory system.  ...  Lateral inhibitory processes are, indeed, primed by large values of b, but their effects are spread over the neural field by diffusive processes, controlled by D.  ... 
doi:10.1016/j.biosystems.2004.09.009 pmid:15649594 fatcat:5ksautc2nvhirncpsdvxqnyo44

Language Modeling on Location-Based Social Networks

Juglar Diaz, Felipe Bravo-Marquez, Barbara Poblete
2022 ISPRS International Journal of Geo-Information  
We define the task of modeling text, timestamps, and geo-coordinates as a spatio-temporal conditioned language model task.  ...  Our experimental results show that each dataset has particular patterns for language generation under spatio-temporal conditions at different granularities.  ...  Unlike static analysis of spatial data, spatio-temporal text data can discover the purpose of a visit to a point of interest that hosts multiple kinds of events.  ... 
doi:10.3390/ijgi11020147 doaj:aa7817b048f843df9ed52dd5fda60fb8 fatcat:w4mb6eb7azbjvmpetwwokesj4q

Comparison Between Two Spatio-Temporal Organization Maps for Speech Recognition [chapter]

Zouhour Neji Ben Salem, Laurent Bougrain, Frédéric Alexandre
2006 Lecture Notes in Computer Science  
In this paper, we compare two models biologically inspired and gathering spatio-temporal data coding, representation and processing.  ...  More precisely, the map is trained using two different spatio-temporal algorithms taking their roots in biological researches: The ST-Kohonen and the Time-Organized Map (TOM).  ...  is introduced for the aim to provide the classical artificial neurons the capacity of processing sequences in asynchronous manner, leading to the emergence of STANN [12] (Spatio-Temporal Artificial Neural  ... 
doi:10.1007/11829898_2 fatcat:ggr6bamlmrbjjgep4sdgzobbu4

Implementing Signature Neural Networks with Spiking Neurons

José Luis Carrillo-Medina, Roberto Latorre
2016 Frontiers in Computational Neuroscience  
The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces.  ...  contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data-to be employed in a spiking neural network.  ...  Different spiking neural networks have been proposed to process, classify, and store spatio-temporal patterns (Laje and Buonomano, 2013; Yu et al., 2013) .  ... 
doi:10.3389/fncom.2016.00132 pmid:28066221 pmcid:PMC5167754 fatcat:mamchuc63baqppe5mb3rdak46i
« Previous Showing results 1 — 15 out of 34,374 results