43,009 Hits in 3.8 sec

Phase-functioned neural networks for character control

Daniel Holden, Taku Komura, Jun Saito
2017 ACM Transactions on Graphics  
We present a real-time character control mechanism using a novel neural network architecture called a Phase-Functioned Neural Network.  ...  In this network structure, the weights are computed via a cyclic function which uses the phase as an input.  ...  PHASE-FUNCTIONED NEURAL NETWORK In this section we discuss the construction and training of the Phase-Functioned Neural Network (PFNN).  ... 
doi:10.1145/3072959.3073663 fatcat:jsmhirwlwfc2lfrjwx5vd2unba

Implementation of Dynamic Artificial Intelligence in Game Development

The most important part of the NN character is the Neural Network Controller which will consist of the Neural network and the other controller functions such as linking the controller with the character  ...  THE NEURAL NETWORK CHARACTER The Neural network character will be similar to the playable character in terms of appearance but with the differance the the character is controlled by a neural network controller  ... 
doi:10.35940/ijitee.k1217.09811s19 fatcat:2avawo4z6ffsfcldgzscbatpfy

Neural state machine for character-scene interactions

Sebastian Starke, He Zhang, Taku Komura, Jun Saito
2019 ACM Transactions on Graphics  
We propose Neural State Machine, a novel data-driven framework to guide characters to achieve goal-driven actions with precise scene interactions.  ...  To increase the precision to reach the goal during runtime, we introduce a control scheme that combines egocentric inference and goal-centric inference.  ...  is to let the neural network learn distinct cyclic/non-cyclic phase functions suitable for different actions and goals, instead of using a single, fixed cyclic function as in PFNN [Holden et al. 2017  ... 
doi:10.1145/3355089.3356505 fatcat:njyujaqlgvhlteg4gjoufeid6a

Adaptive B-spline network control for three-phase PWM AC-DC voltage source converter

K.W.E. Cheng, H.Y. Wang, D. Sutanto
1999 Proceedings of the IEEE 1999 International Conference on Power Electronics and Drive Systems. PEDS'99 (Cat. No.99TH8475)  
A neural network control methodadaptive Bspline neural network for three-phase AC-DC voltage source converters that realizes a sinusoidal ac input current and unity power factor is discussed in this paper  ...  Comparing to the other PWM techniques, the main advantage of the neural network is that it has excellent merit for nonlinear control and is adaptive enough to fit the environment change.  ...  ACKNOWLEDGEMENT The authors gratefully acknowledge the financial support of the Hong Kong Polytechnic University for this project.  ... 
doi:10.1109/peds.1999.794608 fatcat:hwvb6xrgtvdgrmy66aff3wtuzi

License Plate Recognition System using Back Propagation Neural Network

Vijay Laxmi, Harish Rohil
2014 International Journal of Computer Applications  
In this paper, Haar wavelet and back propagation neural network are used for license plate detection and feature extraction of license plate characters.  ...  In recent years, template matching was used for license plate recognition but it is sensitive to noise. So, neural networks are used for recognition.  ...  Back Propagation Neural Network Neural network is a mathematical model that is inspired by the structure and functional aspects of biological neural networks.  ... 
doi:10.5120/17395-7945 fatcat:yllptjyo6ncqfmlrv3ccvmzzim

Presenting a Deep Motion Blending Approach for Simulating Natural Reach Motions [article]

Felix Gaisbauer, Philipp Froehlich, Jannes Lehwald, Philipp Agethen, Enrico Rukzio
2018 Eurographics State of the Art Reports  
In this paper, we propose a novel deep blending approach to simulate non-cyclical natural reach motions based on an extension of phase functioned deep neural networks.  ...  With ongoing progress in artificial intelligence and neural networks, recent works present deep learning based approaches for motion synthesis, which offer great potential for modeling natural motions,  ...  Phase Functioned Neural Network The proposed approach extends the concept of phase functioned neural networks, being first introduced by Holden et al. [HKS17] .  ... 
doi:10.2312/egp.20181010 fatcat:qtgcc6iln5hx7adrmjtt5xxwaq

Usage of Real Time Machine Vision in Rolling Mill

Jiří David, Pavel Švec, Vít Pasker, Romana Garzinová
2021 Sustainability  
The method of optical character recognition using artificial neural networks is the basic algorithm of the system of automatic identification of billets and eliminates ambiguities during their further  ...  the control system.  ...  The neural network works in two basic phases [7] : • Learning phase: (a) adjusting weights according to input patterns; (b) repeating the learning process.  ... 
doi:10.3390/su13073851 fatcat:5efjyrk6qzde5pws4sq4of6g5q


2013 Journal of Computer Science  
The method mostly used for character recognition is the backpropagation network.  ...  The accuracy in recognizing character differ by 10, 77%, with a success rate of 90, 77% for the optimized backpropagation and 80% accuracy for the standard backpropagation network.  ...  This paper presents a new approach in optimizing backpropagation neural network training for optical character recognition.  ... 
doi:10.3844/jcssp.2013.1435.1442 fatcat:do4raryerfcjrgx3vhvw2lxway

Handwritten Character Recognition using Different Kernel based SVM Classifier and MLP Neural Network (A COMPARISON)

Parveen Kumar, Nitin Sharma, Arun Rana
2012 International Journal of Computer Applications  
Character data is used for training the neural network and SVM. The trained network is used for classification and recognition.  ...  For the neural network, each character is resized into 70x50 pixels, which is directly subjected to training.  ...  Of the several Kernel function used in SVM for classifying the characters, the linear kernel function yields the highest recognition accuracy of 94.8 and this accuracy is more than the neural network model  ... 
doi:10.5120/8466-2387 fatcat:wq4lkqa6fvbuth6tounkqldnhu

Evolving artificial neural networks that develop in time [chapter]

Stefano Nolfi, Domenico Parisi
1995 Lecture Notes in Computer Science  
which dictate early maturation of functional neural structure but not of nonfunctional structure.  ...  which dictate early maturation of functional neural structure but not of nonfunctional structure.  ...  (Functional units are units that are part of the functional network while nonfunctional units are part of the nonfunctional neural structure.)  ... 
doi:10.1007/3-540-59496-5_311 fatcat:7ft75iw47nak7j3c6j467mzvum

Biomimetic Underwater Vehicle Modeling Based on Neural Network

Liuji Shang, Shuo Wang, Xiang Dong, Min Tan
2011 IFAC Proceedings Volumes  
This paper introduces the basic control methods of a Biomimetic Underwater Vehicle, and a neural network model is designed for the vehicle.  ...  Based on analysis of the experimental thrust data, linear function is used as activation function of the neurons. Finally, experimental data are used for neural network training and validation.  ...  Based on thrust experimental results, linear function is used as activation function for the neural network layers.  ... 
doi:10.3182/20110828-6-it-1002.00382 fatcat:nnhtpg2sv5gkbiod6n4vkrnvxq

Page 695 of Mathematical Reviews Vol. , Issue 99a [page]

1991 Mathematical Reviews  
Using the Lyapunov function method, they study the properties of stability and convergence for the neural network system.  ...  The book begins with a review of electrical circuits, focusing on voltage-controlled oscillators (VCOs), where the time derivative of the output phase is a linear function of the input voltage.  ... 

Controlling Chaos in a Neural Network Based on the Phase Space Constraint

Guoguang He, Zhitong Cao, Hongping Chen, Ping Zhu
2003 International Journal of Modern Physics B  
In this paper, the phase space constraint method focused on the chaotic neural network is proposed. By analyzing the orbital of the network in phase space, we chose a part of states to be disturbed.  ...  The computer simulation proves that the chaos in the chaotic neural network can be controlled with above method and the network can converge in one of its stored patterns or their reverses which has the  ...  Compared to the Hopfield neural network, the chaotic neural network possesses the characters of larger memory content and good tolerance, etc.  ... 
doi:10.1142/s0217979203022192 fatcat:nzwjqvbksjcbzd6agzxhpps35u

License Plate Character Recognition System using Neural Network

Anuja P. Nagare
2011 International Journal of Computer Applications  
This paper uses two Neural Network techniques for character recognition, one is Back Propagation Neural Network and other one is Learning Vector Quantization Neural Network.  ...  FEATURE EXTRACTION In this paper, as Neural Network is used for character recognition, Feature Extraction is an important step for training and simulating the Neural Network.  ... 
doi:10.5120/3147-4345 fatcat:66okb6sblrhejpqo7zepwnyjvy

Complex networks of simple neurons for bipedal locomotion

Brian Allen, Petros Faloutsos
2009 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The resulting networks are then examined to discover neural structures that arise unusually often, lending some insight into the workings of otherwise opaque controllers. 978-1-4244-3804-4/09/$25.00 ©2009  ...  Our approach exchanges complexity of the neuron model for complexity of the network, gradually building a network of simple neurons capable of complex behaviors.  ...  CONCLUSION This work presents evolved neural network controllers that show smooth motion, without the stiffness and phase artifacts generally associated with methods based on a fixed set of phases or states  ... 
doi:10.1109/iros.2009.5354077 dblp:conf/iros/AllenF09 fatcat:fs4yjvbfzjh4vphxpqafrhrvye
« Previous Showing results 1 — 15 out of 43,009 results