Loading...
Search for:
input-space
0.007 seconds
Model Based Testing in Software Product Line
, M.Sc. Thesis Sharif University of Technology ; Mirian-Hosseinabadi, Hassan (Supervisor)
Abstract
Software product line (SPL) engineering offers several advantages such as reduced costs, high quality and less time to market in development of family of software products. The goal of software product line is systematic and effective development of a set of software products which share common and managed set of features. Software product line testing has its special challenges such as scalability and variability, and has significant importance due to the importance of quality in software product line and enormous number of possible products. Most of the popular methods in this domain have shortcomings such as having seam between development and testing processes, limited application scope...
A Semi-Automated Software Testing Using Input Space Partitioning
, M.Sc. Thesis Sharif University of Technology ; Mirian Hosseinabadi, Hassan (Supervisor)
Abstract
It's impossible to check all inputs of a software program due to infinite input domain, therefore the domain should be somehow restricted. One popular approach to do so, is input space partitioning. In this approach, the input domain has been modeled and partitioned into some equivalent classes or blocks. Using these blocks, it's possible to select one sample from each one and reduce the number of test cases to a small desirable number. To automate this approach, it's essential to firstly define the software requirements specification in a well-defined machine understandable template, then with processing this document we can detect program’s functionality and testable functions. Our goal in...
Metric learning for graph based semi-supervised human pose estimation
, Article Proceedings - International Conference on Pattern Recognition ; 2012 , Pages 3386-3389 ; 10514651 (ISSN) ; 9784990644109 (ISBN) ; Rabiee, H. R ; Zolfaghari, M ; Sharif University of Technology
2012
Abstract
Discriminative approaches to human pose estimation have became popular in recent years. These approaches face a big challenge: Similar inputs might correspond to very dissimilar poses. This property misleads the mapping functions which rely on the Euclidean distances in the input space. In this paper, we use the distances between the labels of the training data to learn a metric and map the input data to a space where this problem is minimized. Our mapping is linear and hence preserves the manifold structure of the input data. We benefit from the unlabeled data to estimate this manifold in the new space as a nearest neighbor graph. We finally utilize Tikhonov regularization to find a smooth...
Graph based semi-supervised human pose estimation: When the output space comes to help
, Article Pattern Recognition Letters ; Volume 33, Issue 12 , September , 2012 , Pages 1529-1535 ; 01678655 (ISSN) ; Rabiee, H. R ; Faghri, F ; Rohban, M. H ; Sharif University of Technology
Elsevier
2012
Abstract
In this letter, we introduce a semi-supervised manifold regularization framework for human pose estimation. We utilize the unlabeled data to compensate for the complexities in the input space and model the underlying manifold by a nearest neighbor graph. We argue that the optimal graph is a subgraph of the k nearest neighbors (k-NN) graph. Then, we estimate distances in the output space to approximate this subgraph. In addition, we use the underlying manifold of the points in the output space to introduce a novel regularization term which captures the correlation among the output dimensions. The modified graph and the proposed regularization term are utilized for a smooth regression over...
A biologically plausible learning method for neurorobotic systems
, Article 2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09, Antalya, 29 April 2009 through 2 May 2009 ; 2009 , Pages 128-131 ; 9781424420735 (ISBN) ; Vosoughi Vahdat, B ; National Institutes of Health, NIH; National Institute of Neurological Disorders and Stroke, NINDS; National Science Foundation, NSF ; Sharif University of Technology
2009
Abstract
This paper introduces an incremental local learning algorithm inspired by learning in neurobiological systems. This algorithm has no training phase and learns the world during operation, in a lifetime manner. It is a semi-supervised algorithm which combines soft competitive learning in input space and linear regression with recursive update in output space. This method is also robust to negative interference and compromises bias-variance dilemma. These qualities make the learning method a good nonlinear function approximator having possible applications in neuro-robotic systems. Some simulations illustrate the effectiveness of the proposed algorithm in function approximation, time-series...