scholarly journals New multivalued functional decomposition algorithms based on MDDs

2000 ◽  
Vol 19 (9) ◽  
pp. 1081-1086 ◽  
Author(s):  
C.M. Files ◽  
M.A. Perkowski
Keyword(s):  
Decomposition Algorithms ◽  
Functional Decomposition ◽  
Multivalued Functional

FUNCTIONAL DECOMPOSITION AND ITS APPLICATIONS IN MACHINE LEARNING AND NEURAL NETWORKS

2001 ◽  
Vol 01 (03) ◽  
pp. 259-271 ◽  
Author(s):  
H. SELVARAJ ◽  
P. SAPIECHA ◽  
T. ŁUBA
Keyword(s):  
Neural Networks ◽  
Computer Aided Design ◽  
Digital Circuits ◽  
Logic Synthesis ◽  
Computer Experiments ◽  
Digital Circuit ◽  
Decomposition Algorithms ◽  
Functional Decomposition ◽  
Training Time ◽  
Aided Design

In this paper, we will begin with an overview of functional decomposition algorithms based on different graph coloring heuristics. We will then discuss the applications of decomposition strategy for the computer aided design of digital circuits and for the supervised learning of neural networks. While decomposition was used successfully in logic synthesis for several years, its application in the area of neural networks is a novel and promising approach. The computer experiments will show significant benefits in mini mization of silicon space required for digital circuit implementation as well as in reduction of training time for neural networks.

Decomposition of tasks in a group of robots using cloud computing technologies

2017 ◽  
Vol 12 (1) ◽  
pp. 83-88
Author(s):  
O.V. Darintsev ◽  
A.B. Migranov
Keyword(s):  
Cloud Computing ◽  
Experimental Verification ◽  
Decomposition Algorithms ◽  
Complex Task ◽  
Large Problem ◽  
Working Capacity ◽  
Linear Distribution ◽  
Effective Teams ◽  
Computing Technologies

In this paper, various variants of decomposition of tasks in a group of robots using cloud computing technologies are considered. The specifics of the field of application (teams of robots) and solved problems are taken into account. In the process of decomposition, the solution of one large problem is divided into a solution of a series of smaller, simpler problems. Three ways of decomposition based on linear distribution, swarm interaction and synthesis of solutions are proposed. The results of experimental verification of the developed decomposition algorithms are presented, the working capacity of methods for planning trajectories in the cloud is shown. The resulting solution is a component of the complex task of building effective teams of robots.

scholarly journals ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

2021 ◽  
Author(s):  
Anil S. Baslamisli ◽  
Partha Das ◽  
Hoang-An Le ◽  
Sezer Karaoglu ◽  
Theo Gevers
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
State Of The Art ◽  
Image Decomposition ◽  
Natural Environments ◽  
Decomposition Algorithms ◽  
Ambient Light ◽  
Fine Grained ◽  
Large Scale Dataset ◽  
Direct Illumination

AbstractIn general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in distinguishing strong photometric effects from reflectance variations. Therefore, in this paper, we propose to decompose the shading component into direct (illumination) and indirect shading (ambient light and shadows) subcomponents. The aim is to distinguish strong photometric effects from reflectance variations. An end-to-end deep convolutional neural network (ShadingNet) is proposed that operates in a fine-to-coarse manner with a specialized fusion and refinement unit exploiting the fine-grained shading model. It is designed to learn specific reflectance cues separated from specific photometric effects to analyze the disentanglement capability. A large-scale dataset of scene-level synthetic images of outdoor natural environments is provided with fine-grained intrinsic image ground-truths. Large scale experiments show that our approach using fine-grained shading decompositions outperforms state-of-the-art algorithms utilizing unified shading on NED, MPI Sintel, GTA V, IIW, MIT Intrinsic Images, 3DRMS and SRD datasets.

scholarly journals Supporting resilient conceptual design using functional decomposition and conflict resolution

2021 ◽  
Vol 48 ◽  
pp. 101262
Author(s):  
Xin Guo ◽  
Ying Liu ◽  
Wu Zhao ◽  
Jie Wang ◽  
Ling Chen
Keyword(s):  
Conflict Resolution ◽  
Conceptual Design ◽  
Functional Decomposition

scholarly journals Robust Template Decomposition without Weight Restriction for Cellular Neural Networks Implementing Arbitrary Boolean Functions Using Support Vector Classifiers

2013 ◽  
Vol 2013 ◽  
pp. 1-9
Author(s):  
Yih-Lon Lin ◽  
Jer-Guang Hsieh ◽  
Jyh-Horng Jeng
Keyword(s):  
Neural Networks ◽  
Boolean Function ◽  
Past Research ◽  
Cellular Neural Network ◽  
Decomposition Methods ◽  
Cellular Neural Networks ◽  
Support Vector ◽  
Decomposition Algorithms ◽  
Weight Restriction ◽  
The Given

If the given Boolean function is linearly separable, a robust uncoupled cellular neural network can be designed as a maximal margin classifier. On the other hand, if the given Boolean function is linearly separable but has a small geometric margin or it is not linearly separable, a popular approach is to find a sequence of robust uncoupled cellular neural networks implementing the given Boolean function. In the past research works using this approach, the control template parameters and thresholds are restricted to assume only a given finite set of integers, and this is certainly unnecessary for the template design. In this study, we try to remove this restriction. Minterm- and maxterm-based decomposition algorithms utilizing the soft margin and maximal margin support vector classifiers are proposed to design a sequence of robust templates implementing an arbitrary Boolean function. Several illustrative examples are simulated to demonstrate the efficiency of the proposed method by comparing our results with those produced by other decomposition methods with restricted weights.

Sign in / Sign up

Export Citation Format

Share Document