Farzad Rastegar - Academia.edu (original) (raw)

Uploads

Papers by Farzad Rastegar

5th International Conference on Modern Developments in Management, Economics and Accounting, 2022

When we hear the term “knowledge”, we might think of all that we learned at school. But there are... more When we hear the term “knowledge”, we might think of all that we learned at school. But there are more sides to this term. These sides might not have had the chance to reveal themselves to us as individuals in our personal lives or employees, managers and executives in organizations. What is knowing? Our discussions seek to address this question through Paul Tillich’s works on the polarity of cognitive reason. We discuss the elements of union and detachment involved in every act of knowledge in humans. Moreover, we illustrate two types of knowledge: controlling knowledge and receiving knowledge. While controlling knowledge values the role of detachment in acts of knowledge, in receiving knowledge union has the dominant role. This essay attempts to make effective use of Watson, a software technology which can build a knowledge base for answering questions. We believe Watson can make our discussions more tangible and understandable. We do not intend, however, to discuss any technical details in the realm of artificial intelligence in this essay.

International Journal of Information and Education Technology, 2016

In this study we look into the socio-political trends emerging after the 1979 revolution in Iran.... more In this study we look into the socio-political trends emerging after the 1979 revolution in Iran. The development of democracy, education, and health network system are remarkable achievements in the Islamic government. However, since economic factors in a society work in harmony, an integrated view about emerging trends results in more achievements and better future planning. This study seeks to bring a set of relevant trends to attention and present a multidimensional picture of Iranian society.

9th IASTED international conference on artificial intelligence and soft computing (ASC'05), 2005

12th International Computer Society of Iran Computer Conference (CSICC'07), 2006

In several previous studies it has been shown that the generalization capabilities of humans thro... more In several previous studies it has been shown that the generalization capabilities of humans through concept learning is reminiscent of Bayesian modeling. When discriminating concepts from one another, human subjects tend to focus on the relevant features of the subspace and ignore the irrelevant ones. In this paper we propose a Bayesian concept learning paradigm that utilizes unrestricted Bayesian networks to learn the required concepts for optimal decision making. This approach has several beneficial characteristics that a concept learning algorithm should hold. At first it can both learn form observing an expert performing the desired task and from its own experience while carrying it out. Secondly, it is a close and computationally feasible approximation to the Bayesian modeling capabilities of humans. Thirdly, the Markov blanket surrounding the decision variable can render the irrelevant features independent and therefore this approach can ignore them seamlessly from the feature subspace. The simulation and experimental results are promising and show that our approach can successfully extract the required temporally extended concepts for a mobile robot task.

The 12th IEEE congress on evolutionary computation (CEC'05), 2005

This paper proposes a cooperative evolutionary method for optimizing the properties of an ANFISar... more This paper proposes a cooperative evolutionary method for optimizing the properties of an ANFISarchitecture-based model where only the input-output data of the identified system are available. The primary tasks of fuzzy modeling are structure identification and parameter optimization: the former determines the numbers of membership functions and fuzzy if-then rules while the latter identifies a feasible set of parameters under the given structure. The proposed approach manages all mentioned attributes simultaneously. Particularly, number of rules and parameters of membership functions are realized by applying a novel approach using genetic programming and genetic algorithm whereas consequent parameters are tuned by using least-squares estimation. Finally, two examples of nonlinear system are given to illustrate the effectiveness of the proposed approach.

17th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'05), 2005

A game is a decision-making situation in which each player attempts to act in such a way that the... more A game is a decision-making situation in which each player attempts to act in such a way that the game's circumstances get close to what desirable for him. To reach this goal, a player needs to have a suitable estimation of the other players' decisions. In this paper we propose a fuzzy approach by which a player can attain an

2007 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, 2007

In order to make appropriate decisions, intelligent creatures narrow their sensory information do... more In order to make appropriate decisions, intelligent creatures narrow their sensory information down to high-level, abstract knowledge. Inspired by recent findings in neuroscience on the role of mirror neurons in action-based abstraction, in this study we propose a two-phase framework whereby a reinforcement learning (RL) agent attempts to understand its environment via meaningful temporally extended concepts in an unsupervised way.

In several previous studies it has been shown that the generalization capabilities of humans thro... more In several previous studies it has been shown that the generalization capabilities of humans through concept learning is reminiscent of Bayesian modeling. When discriminating concepts from one another, human subjects tend to focus on the relevant features of the subspace and ignore the irrelevant ones. In this paper we propose a Bayesian concept learning paradigm that utilizes unrestricted Bayesian networks to learn the required concepts for optimal decision making. This approach has several beneficial characteristics that a concept learning algorithm should hold. At first it can both learn form observing an expert performing the desired task and from its own experience while carrying it out. Secondly, it is a close and computationally feasible approximation to the Bayesian modeling capabilities of humans. Thirdly, the Markov blanket surrounding the decision variable can render the irrelevant features independent and therefore this approach can ignore them seamlessly from the feature subspace. The simulation and experimental results are promising and show that our approach can successfully extract the required temporally extended concepts for a mobile robot task.

5th International Conference on Modern Developments in Management, Economics and Accounting, 2022

When we hear the term “knowledge”, we might think of all that we learned at school. But there are... more When we hear the term “knowledge”, we might think of all that we learned at school. But there are more sides to this term. These sides might not have had the chance to reveal themselves to us as individuals in our personal lives or employees, managers and executives in organizations. What is knowing? Our discussions seek to address this question through Paul Tillich’s works on the polarity of cognitive reason. We discuss the elements of union and detachment involved in every act of knowledge in humans. Moreover, we illustrate two types of knowledge: controlling knowledge and receiving knowledge. While controlling knowledge values the role of detachment in acts of knowledge, in receiving knowledge union has the dominant role. This essay attempts to make effective use of Watson, a software technology which can build a knowledge base for answering questions. We believe Watson can make our discussions more tangible and understandable. We do not intend, however, to discuss any technical details in the realm of artificial intelligence in this essay.

International Journal of Information and Education Technology, 2016

In this study we look into the socio-political trends emerging after the 1979 revolution in Iran.... more In this study we look into the socio-political trends emerging after the 1979 revolution in Iran. The development of democracy, education, and health network system are remarkable achievements in the Islamic government. However, since economic factors in a society work in harmony, an integrated view about emerging trends results in more achievements and better future planning. This study seeks to bring a set of relevant trends to attention and present a multidimensional picture of Iranian society.

9th IASTED international conference on artificial intelligence and soft computing (ASC'05), 2005

12th International Computer Society of Iran Computer Conference (CSICC'07), 2006

In several previous studies it has been shown that the generalization capabilities of humans thro... more In several previous studies it has been shown that the generalization capabilities of humans through concept learning is reminiscent of Bayesian modeling. When discriminating concepts from one another, human subjects tend to focus on the relevant features of the subspace and ignore the irrelevant ones. In this paper we propose a Bayesian concept learning paradigm that utilizes unrestricted Bayesian networks to learn the required concepts for optimal decision making. This approach has several beneficial characteristics that a concept learning algorithm should hold. At first it can both learn form observing an expert performing the desired task and from its own experience while carrying it out. Secondly, it is a close and computationally feasible approximation to the Bayesian modeling capabilities of humans. Thirdly, the Markov blanket surrounding the decision variable can render the irrelevant features independent and therefore this approach can ignore them seamlessly from the feature subspace. The simulation and experimental results are promising and show that our approach can successfully extract the required temporally extended concepts for a mobile robot task.

The 12th IEEE congress on evolutionary computation (CEC'05), 2005

This paper proposes a cooperative evolutionary method for optimizing the properties of an ANFISar... more This paper proposes a cooperative evolutionary method for optimizing the properties of an ANFISarchitecture-based model where only the input-output data of the identified system are available. The primary tasks of fuzzy modeling are structure identification and parameter optimization: the former determines the numbers of membership functions and fuzzy if-then rules while the latter identifies a feasible set of parameters under the given structure. The proposed approach manages all mentioned attributes simultaneously. Particularly, number of rules and parameters of membership functions are realized by applying a novel approach using genetic programming and genetic algorithm whereas consequent parameters are tuned by using least-squares estimation. Finally, two examples of nonlinear system are given to illustrate the effectiveness of the proposed approach.

17th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'05), 2005

A game is a decision-making situation in which each player attempts to act in such a way that the... more A game is a decision-making situation in which each player attempts to act in such a way that the game's circumstances get close to what desirable for him. To reach this goal, a player needs to have a suitable estimation of the other players' decisions. In this paper we propose a fuzzy approach by which a player can attain an

2007 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, 2007

In order to make appropriate decisions, intelligent creatures narrow their sensory information do... more In order to make appropriate decisions, intelligent creatures narrow their sensory information down to high-level, abstract knowledge. Inspired by recent findings in neuroscience on the role of mirror neurons in action-based abstraction, in this study we propose a two-phase framework whereby a reinforcement learning (RL) agent attempts to understand its environment via meaningful temporally extended concepts in an unsupervised way.

In several previous studies it has been shown that the generalization capabilities of humans thro... more In several previous studies it has been shown that the generalization capabilities of humans through concept learning is reminiscent of Bayesian modeling. When discriminating concepts from one another, human subjects tend to focus on the relevant features of the subspace and ignore the irrelevant ones. In this paper we propose a Bayesian concept learning paradigm that utilizes unrestricted Bayesian networks to learn the required concepts for optimal decision making. This approach has several beneficial characteristics that a concept learning algorithm should hold. At first it can both learn form observing an expert performing the desired task and from its own experience while carrying it out. Secondly, it is a close and computationally feasible approximation to the Bayesian modeling capabilities of humans. Thirdly, the Markov blanket surrounding the decision variable can render the irrelevant features independent and therefore this approach can ignore them seamlessly from the feature subspace. The simulation and experimental results are promising and show that our approach can successfully extract the required temporally extended concepts for a mobile robot task.