Technion – Israel Institute of Technology

About: Technion – Israel Institute of Technology is a education organization based out in Haifa, Israel. It is known for research contribution in the topics: Population & Nonlinear system. The organization has 31714 authors who have published 79377 publications receiving 2603976 citations. The organization is also known as: Technion Israel Institute of Technology & Ṭekhniyon, Makhon ṭekhnologi le-Yiśraʼel.

Experimental Investigation of Laser Surface Texturing for Reciprocating Automotive Components

Abstract: An experimental study is presented to evaluate the effectiveness of micro-surface structure, produced by laser texturing, to improve tribological properties of reciprocating automotive components. The test rig and test specimens are described and some test results are presented. Good correlation is found with theoretical prediction of friction reduction on a simple, yet representative, test specimen. Potential benefit of the laser surface texturing under conditions of lubricant starvation is also presented. Finally, friction reduction with actual production piston rings and cylinder liner segments is demonstrated. Presented at the 57th Annual Meeting in Houston, Texas May 19–23, 2002

Mean shift based clustering in high dimensions: a texture classification example

Abstract: Feature space analysis is the main module in many computer vision tasks. The most popular technique, k-means clustering, however, has two inherent limitations: the clusters are constrained to be spherically symmetric and their number has to be known a priori. In nonparametric clustering methods, like the one based on mean shift, these limitations are eliminated but the amount of computation becomes prohibitively large as the dimension of the space increases. We exploit a recently proposed approximation technique, locality-sensitive hashing (LSH), to reduce the computational complexity of adaptive mean shift. In our implementation of LSH the optimal parameters of the data structure are determined by a pilot learning procedure, and the partitions are data driven. As an application, the performance of mode and k-means based textons are compared in a texture classification study.

Computational capabilities of recurrent NARX neural networks

Abstract: Recently, fully connected recurrent neural networks have been proven to be computationally rich-at least as powerful as Turing machines. This work focuses on another network which is popular in control applications and has been found to be very effective at learning a variety of problems. These networks are based upon Nonlinear AutoRegressive models with eXogenous Inputs (NARX models), and are therefore called NARX networks. As opposed to other recurrent networks, NARX networks have a limited feedback which comes only from the output neuron rather than from hidden states. They are formalized by y(t)=/spl Psi/(u(t-n/sub u/), ..., u(t-1), u(t), y(t-n/sub y/), ..., y(t-1)) where u(t) and y(t) represent input and output of the network at time t, n/sub u/ and n/sub y/ are the input and output order, and the function /spl Psi/ is the mapping performed by a Multilayer Perceptron. We constructively prove that the NARX networks with a finite number of parameters are computationally as strong as fully connected recurrent networks and thus Turing machines. We conclude that in theory one can use the NARX models, rather than conventional recurrent networks without any computational loss even though their feedback is limited. Furthermore, these results raise the issue of what amount of feedback or recurrence is necessary for any network to be Turing equivalent and what restrictions on feedback limit computational power.