Loading...
Search for:
haghzad-klidbary--sajad
0.062 seconds
A novel adaptive learning algorithm for low-dimensional feature space using memristor-crossbar implementation and on-chip training
, Article Applied Intelligence ; Volume 48, Issue 11 , 2018 , Pages 4174-4191 ; 0924669X (ISSN) ; Bagheri Shouraki, S ; Sharif University of Technology
2018
Abstract
Proposing an efficient algorithm with an appropriate hardware implementation has always been an interesting and a rather challenging field of research in Artificial Intelligence (AI). Fuzzy logic is one of the techniques that can be used for accurate and high-speed modeling as well as controlling complex and nonlinear systems. The “defuzzification” process during the test phase as well as the repetitive processes in order to find the optimal parameters during the training phase, lead to some serious limitations in real-time applications and hardware implementation of these algorithms. The proposed algorithm employs Ink Drop Spread (IDS) concept to mimic the functionality of human brain. In...
Path planning of modular robots on various terrains using Q-learning versus optimization algorithms
, Article Intelligent Service Robotics ; Volume 10, Issue 2 , 2017 , Pages 121-136 ; 18612776 (ISSN) ; Bagheri Shouraki, S ; Sheikhpour Kourabbaslou, S ; Sharif University of Technology
Springer Verlag
2017
Abstract
Self-reconfigurable modular robots (SRMRs) have recently attracted considerable attention because of their numerous potential applications in the real world. In this paper, we draw a comprehensive comparison among five different algorithms in path planning of a novel SRMR system called ACMoD through an environment comprised of various terrains in a static condition. The contribution of this work is that the reconfiguration ability of ACMoD has been taken into account. This consideration, though raises new algorithmic challenges, equips the robot with new capability to pass difficult terrains rather than bypassing them, and consequently the robot can achieve better performance in terms of...
Finding Proper Modular Robots Structure by Using Genetic Algorithm
,
M.Sc. Thesis
Sharif University of Technology
;
Bagheri Shouraki, Saeed
(Supervisor)
Abstract
Modular Robots are group of robots which are made of small components called modules. The advantage of these robots to others is their ability to change physical configuration. Using of these robots in configuration changing due to environmental conditions is popular. While, reconfiguration is one of the most important features in modular robot, it’s the most important concern too. Path planning problem is one of the important problems in robotics .So far, most of presented path planning methods and algorithms are based on fixed-structure and they had little attention to path planning and configuration changing, simultaneously. In this thesis, the Genetic Algorithm is used to find path and...
Alm Improvement Based On New Fuzzy Operator With Memristor Implementation Capability
, Ph.D. Dissertation Sharif University of Technology ; Bagheri Shouraki, Saeed (Supervisor)
Abstract
Designing artificial intelligence based arithmetic machines that can intelligently perform human-like task has attracted considerable interest among researchers. The ever-increasing advances in soft-computing algorithms require appropriate hardware platforms for such algorithms. One of the most important problems with these algorithms and their hardware implementation structures is the discrepancy between the hardware and the nature of the problem. It can be argued that paying attention to hardware implementation does not necessarily guarantee an optimal implementation of these algorithms. Most of the proposed hardware implementations have very small resemblance to the biological systems...
An adaptive efficient memristive ink drop spread (IDS) computing system
, Article Neural Computing and Applications ; Volume 31, Issue 11 , 2019 , Pages 7733-7754 ; 09410643 (ISSN) ; Bagheri Shouraki, S ; Esmaili Paeen Afrakoti, I ; Sharif University of Technology
Springer London
2019
Abstract
Active Learning Method (ALM) is one of the powerful tools in soft computing and it is inspired by the human brain capabilities in approaching complicated problems. ALM, which is in essence an adaptive fuzzy learning algorithm, tries to model a Multi-Input Single-Output system with several single-input single-output subsystems. Each of these subsystems is then modeled by an ink drop spread (IDS) plane. IDS operator, which is the main processing engine of ALM, extracts two kinds of informative features, Narrow Path and Spread, from each IDS plane without complicated computations. These features from all IDS planes are then aggregated in the inference engine. Despite the great performance of...
An adaptive efficient memristive ink drop spread (IDS) computing system
, Article Neural Computing and Applications ; 2018 , Pages 1-22 ; 09410643 (ISSN) ; Bagheri Shouraki, S ; Esmaili Paeen Afrakoti, I ; Sharif University of Technology
Springer London
2018
Abstract
Active Learning Method (ALM) is one of the powerful tools in soft computing and it is inspired by the human brain capabilities in approaching complicated problems. ALM, which is in essence an adaptive fuzzy learning algorithm, tries to model a Multi-Input Single-Output system with several single-input single-output subsystems. Each of these subsystems is then modeled by an ink drop spread (IDS) plane. IDS operator, which is the main processing engine of ALM, extracts two kinds of informative features, Narrow Path and Spread, from each IDS plane without complicated computations. These features from all IDS planes are then aggregated in the inference engine. Despite the great performance of...
A bridge technique for memristor state programming
, Article International Journal of Electronics ; Volume 107, Issue 6 , 2020 , Pages 1015-1030 ; Maymandi Nejad, M ; Haghzad Klidbary, S ; Bagheri Shouraki, S ; Sharif University of Technology
Taylor and Francis Ltd
2020
Abstract
In order to effectively use a memristor in analog circuits, its memristance should be adjusted to a desired value between its limits. Since the maximum and minimum required memristance typically varies considerably between different types of memristors, it is almost impossible to tune the resistance of each memristor based on a reference resistor. Which is mostly done using some programmer circuits. Moreover, those programming strategies involving pulses are time-consuming and they impose high hardware headroom. In this paper, a novel CMOS circuit is presented for programming memristors. A Wheatstone bridge circuit is used to measure the current memristance, while the programming current is...
Adversarial Attack to Deep Learning Networks via Imperceptible Sparse Perturbation
, M.Sc. Thesis Sharif University of Technology ; Ghaemmaghami, Shahrokh (Supervisor) ; Marvasti, Farokh (Supervisor) ; Amini, Sajad (Co-Supervisor)
Abstract
Nowadays, methods based on deep learning networks are the most effective artificial in telligence methods. Although they have achieved success in various fields (such as machine vision and object recognition), practical and experimental cases show the fragility of deep learning networks against perturbations and unwanted changes of the input pattern. All these perturbations must be in a way that the main class of the perturbed input pattern can be rec ognized by human, but the network makes a mistake in recognizing its correct class. This thesis seeks a more accurate evaluation by designing adversarial attacks such that the main class of the adversarial pattern is detectable by human...
Dynamic response of metal foam FG porous cylindrical micro-shells due to moving loads with strain gradient size-dependency
, Article European Physical Journal Plus ; Volume 134, Issue 5 , 2019 ; 21905444 (ISSN) ; Forsat, M ; Barati, M. R ; Abdella, G. M ; Mohasel Afshari, B ; Hamouda, A. M. S ; Rabby, S ; Sharif University of Technology
Springer Verlag
2019
Abstract
The dynamic characteristics of functionally graded (FG) metal foam cylindrical micro-scale shells in contact with a moving load will be analyzed thorough this paper accounting for strain-gradient size-dependency. In the material structure of a metal foam, pores can diffuse uniformly or non-uniformly. Based upon Laplace transform, the dynamical governing equations of the first-order micro-shell model can be established in a new domain. In order to go back into the time domain, an inverse Laplace transform will be required. Thus, on can express the time response or dynamic deflection of the micro-shell under moving load. In the presented results, it is easy to see the prominence of...