705,607 Hits in 2.6 sec

Neural Production Systems: Learning Rule-Governed Visual Dynamics [article]

Anirudh Goyal, Aniket Didolkar, Nan Rosemary Ke, Charles Blundell, Philippe Beaudoin, Nicolas Heess, Michael Mozer, Yoshua Bengio
2022 arXiv   pre-print
As an alternative, we take inspiration from cognitive science and resurrect a classic approach, production systems, which consist of a set of rule templates that are applied by binding placeholder variables  ...  To model interactions among entities, equivariant graph neural nets (GNNs) are used, but these are not particularly well suited to the task for two reasons.  ...  Neural Production System: Slots and Sparse Rules The Neural Production System (NPS), illustrated in Figure 2 , provides an architectural backbone that supports the detection and inference of entity (object  ... 
arXiv:2103.01937v3 fatcat:f2yu3pfyfzg4zl2j67pxgsqbsq

Expressing uncertainty in neural networks for production systems

Samim Ahmad Multaheb, Bernd Zimmering, Oliver Niggemann
2021 at - Automatisierungstechnik  
This is a prerequisite for the use of such networks in closedcontrol loops and in automation systems.  ...  The application of machine learning, especially of trained neural networks, requires a high level of trust in their results.  ...  But while superficially much data seem to be generated by Cyber Physical Production Systems (CPPSs), a different picture can be seen when ML is applied: Data intensive ML approaches such as neural networks  ... 
doi:10.1515/auto-2020-0122 dblp:journals/at/MultahebZN21 fatcat:euv5rs3gdje6bm7o4dy5qvv4ee


2002 Kansei Engineering International  
Comfortable human interfaces are required for advanced systems. This paper aims at developing a Kansei product design system to support designing keyboard switches based on Kansei.  ...  When we input Kansei data expressed dual scale value, the neural network can output reaction forces to give feeling the inputted Kansei.  ...  CONCLUSION This study developed reaction forces design system based on Kansei, as an example of Kansei product design system using neural network.  ... 
doi:10.5057/kei.3.4_31 fatcat:6v3prtvlt5hhhfsgaigfgnplla

Visual Product Tracking System Using Siamese Neural Networks

Tuomas Jalonen, Firas Laakom, Moncef Gabbouj, Tuomas Puoskari
2021 IEEE Access  
Moreover, to overcome the challenges of visual tracking systems, we rely on a Siamese neural network to match the products.  ...  We propose a visual manufacturing product tracking system utilizing machine learning. 2. We propose a Siamese neural network to learn to match process input and output images. 3.  ... 
doi:10.1109/access.2021.3082934 fatcat:t63z2wwtqzdqzmtbmvb2tlsv44

Products of Edge-perts

Peter V. Gehler, Max Welling
2005 Neural Information Processing Systems  
In this paper we propose a particular kind of probabilistic model, dubbed the "products of edge-perts model" to describe the structure of wavelet transformed images.  ...  Discussion We have proposed a general "product of edge-perts" model to capture the dependency structure in wavelet coefficients.  ...  (IIa) Bottom up network interpretation of "products of edge-perts" model. (IIb) Top-down generative Gaussian scale mixture model.  ... 
dblp:conf/nips/GehlerW05 fatcat:dwits36yuvdilc5rtufqy5idhy

Speech Production Using A Neural Network with a Cooperative Learning Mechanism

Mitsuo Komura, Akio Tanaka
1988 Neural Information Processing Systems  
Using this neural network, we have developed a speech production system consisting of a phonemic symbol production subsystem and a speech parameter production subsystem.  ...  We propose a new neural network model and its learning algorithm. The proposed neural network consists of four layers -input, hidden, output and final output layers.  ...  Cooperative Learning System Figure 2 . 2 Figure 2. The Speech Production System Using the Proposed Neural Network Figure 4.  ... 
dblp:conf/nips/KomuraT88 fatcat:ewlkpigxfzfg5chvauc3z7fcty


В. Єременко, А. Переїденко, В. Роганьков
2011 Vìsnik Nacìonalʹnogo Avìacìjnogo Unìversitetu  
Algorithm of construction and principles of operation demerit rating system which based on hybrid neural network is described.  ...  Use of artificial neural networks for classification of defects in cellular panels was introduced and investigated.  ... 
doi:10.18372/2306-1472.47.18 fatcat:jm2pokbrqfc7fdb7vjz662ttde

The Product Cut

Thomas Laurent, James H. von Brecht, Xavier Bresson, Arthur Szlam
2016 Neural Information Processing Systems  
We refer to this objective as the Product Cut. We provide a detailed investigation of the mathematical properties of this objective and an effective algorithm for its optimization.  ...  Information Processing Systems (NIPS 2016), Barcelona, Spain.  ...  The second key ingredient involves approximating solutions to the linear system M α x = b quickly.  ... 
dblp:conf/nips/0001BBS16 fatcat:m4hiw3jhmjda7iz6yyve2qnb4i

Shallow vs. Deep Sum-Product Networks

Olivier Delalleau, Yoshua Bengio
2011 Neural Information Processing Systems  
We investigate the representational power of sum-product networks (computation networks analogous to neural networks, but whose individual units compute either products or weighted sums), through a theoretical  ...  Such results were not available until now, and contribute to motivate recent research involving learning of deep sum-product networks, and more generally motivate research in Deep Learning.  ...  These networks are analogous to traditional artificial neural networks but with nodes that compute either products or weighted sums of their inputs.  ... 
dblp:conf/nips/DelalleauB11 fatcat:tqgz3xj54ngnhmbw4v5z6tigfq

Products of Gaussians

Christopher K. I. Williams, Felix V. Agakov, Stephen N. Felderhof
2001 Neural Information Processing Systems  
We examine (1) Products of Gaussian pancakes which give rise to probabilistic Minor Components Analysis, (2) products of I-factor PPCA models and (3) a products of experts construction for an AR(l) process  ...  Although the product of Gaussians is also a Gaussian, if each Gaussian has a simple structure the product can have a richer structure.  ...  SNF gratefully acknowledges additional support from BAE Systems.  ... 
dblp:conf/nips/WilliamsAF01 fatcat:gabhio5k3fb25pxwcojlgarhyy

Product Analysis: Learning to Model Observations as Products of Hidden Variables

Brendan J. Frey, Anitha Kannan, Nebojsa Jojic
2001 Neural Information Processing Systems  
Since product analysis is a generalization of factor analysis, product analysis always finds a higher data likelihood than factor analysis.  ...  We describe a nonlinear generalization of factor analysis , called "product analysis", that models the observed variables as a linear combination of products of normally distributed hidden variables.  ...  Mean images learned using b) product analysis c) mixture of gaussians Figure 2 : 2 Figure 2: Images generated from the learned mixture of product analyzers  ... 
dblp:conf/nips/FreyKJ01 fatcat:qzyrh53i2nfpbjvj5dbzvsvdly

How Perception Guides Production in Birdsong Learning

Christopher L. Fry
1995 Neural Information Processing Systems  
how perceptual learning can guide production through reinforcement learning.  ...  It shows how competitive learning may lead to the organization of a specific nucleus in the bird brain, replicates the song production results of a previous model (Doya and Sejnowski, 1995) , and demonstrates  ...  The third song shows that the network was able to learn the template song using the neural responses of the perceptual system to generate the reinforcement signal.  ... 
dblp:conf/nips/Fry95 fatcat:ingsroozqba2fliyfnrwnhcrwu

Discriminative Learning of Sum-Product Networks

Robert Gens, Pedro M. Domingos
2012 Neural Information Processing Systems  
Sum-product networks are a new deep architecture that can perform fast, exact inference on high-treewidth models. Only generative methods for training SPNs have been proposed to date.  ...  It is commonly observed in neural networks that when the gradient is propagated to lower layers it becomes less informative [3] .  ...  We compare top CIFAR-10 results in Table 3 , highlighting the dictionary size of systems that use the feature extraction from Coates et al. [10] .  ... 
dblp:conf/nips/GensD12 fatcat:desxss2v5bci7krbl3rqpfgicy

Online Sum-Product Computation Over Trees

Mark Herbster, Stephen Pasteris, Fabio Vitale
2012 Neural Information Processing Systems  
We consider the problem of performing efficient sum-product computations in an online setting over a tree.  ...  We accomplish this via a hierarchical covering structure that caches previous local sum-product computations.  ...  Note: if for γa(v) if the product is empty then the product evaluates to 1; and if v ∈ C1 then a (v) := 1. 5 The construction of the decomposition tree may be simultaneously accomplished with the same  ... 
dblp:conf/nips/HerbsterPV12 fatcat:6jlgp67zljgghexkrjxztu56wa

Artificial Neural Networks in Production Scheduling and Yield Prediction of Semiconductor Wafer Fabrication System [chapter]

Jie Zhang, Junliang Wang, Wei Qin
2016 Artificial Neural Networks - Models and Applications  
The production scheduling and yield prediction are two critical issues in the operation of semiconductor wafer fabrication system (SWFS).  ...  This chapter proposed two fuzzy neural networks for the production rescheduling strategy decision and the die yield prediction.  ...  The production scheduling and yield prediction of semiconductor wafer fabrication system (SWFS) The semiconductor wafer fabrication system (SWFS) is one of the most sophisticated manufacturing systems.  ... 
doi:10.5772/63444 fatcat:nwamcuafkzgp3fysvfagug5wjy
« Previous Showing results 1 — 15 out of 705,607 results