Abstract: Programming mobile robots can be long and difficult task. The idea of having a robot learn how to accomplish a task, rather than being told explicitly is appealing. TD(λ)
|
Amir massoud Farahmand |
PAGE CONTENT OTHER PLACES |
Not only my research interest, but also my life's greatest question is investigating the way people think. Thus, Artificial Intelligence (or Machine Intelligence which is a better phrase for what I mean) is a suitable scientific research area to go in for me. Therefore, I can specify my research interest as Artificial Intelligence in general and more specifically, different machine learning methods, connectionism viewpoint of mind (so I like Neural Networks), and bio-inspired methods of problem solving like different evolutionary methods. In addition, I like chaos and chaos control as you can see in my technical reports' session. In summary, I can specify following items:
Hierarchical [Reinforcement] Learning in Behavior-based Systems (MS. Thesis) (2003-2005)
Structure Learning
Behavior Learning
Concurrent Behavior and Structure Learning
Behavior Evolution
Concurrent Behavior Evolution and Structure Learning
Automatic Generation of Reinforcement Signal
Evolutionary Robotics
Hybrid Evolution/Learning in Hierarchical Behavior-based Systems (2004-2005)
Evolving Neural Network-based Controllers for Robots (2001)
Investigating the Effect of Reward Uncertainty on the Value and the Policy of the Agent. (2004-2005)
Automatic Abstraction of Knowledge from Stimuli-Response information (2004-2005)
Structural Abstraction
Temporal Abstraction
Synchronization of Chaotic Systems (2003-4)
Stable Fuzzy Controllers (2003)
Combinatorial Optimization Problem (Channel Assignment Problem) using Chaotically-Enhanced Hopfield Neural Network (2002-3)
Calculating Resonant Frequencies of a Metallic Cavity using Finite Element Method (BS Thesis) (2001-2)
Investigating the Effect of Metallic Electrode and Buffer Layer on Dielectric Waveguides (Internship) (2001)
Several Researches on Evolutionary Computation (2000-current)
Evolutionary Robotics
Evolution of Hidden Markov Models (2001)
Distributed Evolutionary Systems (2000)
Electromagnetic Filter Design (2000)
Analog Circuits Design (2000)
PUBLISHED
[1] Amir massoud Farahmand,
Majid Nili Ahmadabadi, and Babak Najar Araabi, "Behavior
Hierarchy Learning in a Behavior-based System using Reinforcement Learning,"
Proceeding of International Conference on Intelligent Robots and Systems
(IROS2004), Sendai, Japan, 2004. (pdf)
Abstract:
Hand-design
of an intelligent agent’s behaviors and their hierarchy is a very hard task. One
of the most important steps toward creating intelligent agents is providing them
with capability to learn the required behaviors and their architecture.
Architecture learning in a behavior-based agent with Subsumption architecture is
considered in this paper. Overall value function is decomposed into easily
calculate-able parts in order to learn the behavior hierarchy. Using
probabilistic formulations, two different decomposition methods are discussed:
storing the estimated value of each behavior in each layer, and storing the
ordering of behaviors in the architecture. Using defined decompositions, two
appropriate credit assignment methods are designed. Finally, the proposed
methods are tested in a multi-robot object-lifting task that results in
satisfactory performance.
[2]
A.M. Farahmand and Majid Nili Ahmadabadi, "The Effect of Reinforcement Signal
Error in Reinforcement Learning," Computer Society of Iran Computer
Conference (CSICC), 2005.
Abstract: Designing reinforcement signal is
fundamental problem in reinforcement learning. Intelligent agent’s designer can
guide the learner agent to its desired behavior by selecting an appropriate
reinforcement signal. However, there is no general methodology for designing
that signal and the designed signal is different from the unknown ideal one in
many cases. In this paper, this difference is considered as a bounded-norm error
in reinforcement signal and its effects on the value function and the policy of
the agent is calculated as some upper bounds. In the end, the mathematical
results are tested in an experiment.
[3] Amir
massoud Farahmand and Caro Lucas, "Fuzzy Neural Network Implementation of Q(λ)
for Mobile Robots," WSEAS Transaction on Systems, Issue 1, Vol. 3, Jan. 2004.
(pdf)
Abstract:
Programming mobile
robots can be long and difficult task. The idea of having a robot learn how to
accomplish a task, rather than being told explicitly is appealing. TD(λ)
[4] Amir massoud Farahmand, Roxana Akhbari, and Maryam Tajvidi, "Evolving Hidden Markov Models," 4th Iranian Student Conference on Electrical Engineering (ISCEE), 2001. (In Persian/Farsi)
[5] Amir massoud Farahmand and Amir Emad Mirmirani, "Distributed Genetic Algorithms," 3rd Iranian Student Conference on Electrical Engineerin (ISCEE), 2000. (In Persian/Farsi)
[6] Amir massoud Farahmand, Majid Nili Ahmadabadi, and Babak N. Araabi, "Behavior and Hierarchy Development in Behavior-based Systems using Reinforcement Learning," submitted.
[7] Amir massoud Farahmand, Majid Nili Ahmadabadi, Caro Lucas, and Babak N. Araabi, "Behavior Evolution and Hierarchy Learning in Behavior-based Systems using Reinforcement Learning and Co-evolutionary Mechanism," submitted.
[8] Amir massoud Farahmand and Babak Najar
Araabi, "Chaos Control Survey," a technical survey for my seminar's
course, 2004 (in Persian).
[9] Amir massoud Farahmand and Parviz Jabehdar
Maralani, "Stabilizing Chaotic Systems with Small Control Signal," 2003
(unpublished).
[10] Amir massoud Farahmand and Mohammad Javad
Yazdanpanah, "A Class of Nonlinear Controllers for Synchronization of Chaotic
Semipassive Systems," 2003 (unpublished (it has been waited for a long time
despite that fact that I have ever wished to publish it as soon as possible!)).
[11] Amir massoud Farahmand and Mohammad Javad
Yazdanpanah, "Locally Optimal Takagi-Sugeno Fuzzy Controller," 2003
(unpublished).
[12] Amir massoud Farahmand and Mohammad Javad
Yazdanpanah, "Combinatorial Optimization Problem Using Chaotic Simulated
Annealing Enhanced Hopfield Neural Network," 2003 (unpublished it has been
waited for a long time despite that fact that I have ever wished to publish it
as soon as possible!)).
[13] Amir massoud Farahmand and Mohammad Sadegh
Abrishamian, "Calculating Resonance Frequencies of a Metallic Cavity using
Finite Element Method," My BSEE Thesis, 2002 (In Persian).
[14] Amir massoud Farahmand, Ramin Pashai, and
E. Geranpayeh, "Effect of Metallic Electrode and Buffer Layer on Dielectric
Waveguides," a technical report which was written when I was doing my
Internship at Iran
Telecommunication Research Center (ITRC), 2001.
[15] Amir massoud Farahmand, "Evolutionary
Design of Passive Filters," 2001.
[16] Amir massoud Farahmand, "Optimizing
Multi-layer Dielectric Absorbers using Evolutionary Methods," 2000.
[17] Amir massoud Farahmand, "On
Chaotic Models of Population - a Survey," 1999 (In Persian/Farsi).
[18] Amir massoud Farahmand, "Compression
Methods," (I can call it my first technical report which I started writing
when I was at the last year of high school), 1997 (In Persian/Farsi).
Distributed AI
Neural Networks
Fuzzy Systems
Bio-computing
Adaptive Control
Nonlinear Control
Optimal Control
Multivariable Control
Digital Control
Stochastic Process
Seminar on Chaos Control
Numerical Methods in Electromagnetic
Pattern Recognition (audited)
Robotics (audited)
Advanced Digital Communication (audited)
Talks and Teaching Experiences
I was TA of the following courses:
Signals and Systems (Spring 2001 – Dr. Mohammad sadegh Abrishamian)
Telecommunication I (Spring 2001 – Dr. Esmael Kalantari)
In addition to those official teaching experiences, I have presented following short courses and seminars:
Reinforcement Signal Error in Reinforcement Learning, Poster Presentation, The Computer Society of Iran Computer Conference, Winter 2005.
Concept-Oriented Imitative Learning, The Computer Society of Iran Computer Conference, Winter 2005 (presented instead of Hossein Mobahi).
Learning and Evolution in Behavior-based Systems, Institute of Physics and Mathematics (IPM) monthly seminars on Machine Learning, Winter 2005.
Behavior Hierarchy Learning in a Behavior-based System Using Reinforcement Learning, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2004, Oct. 2004.
Hierarchical Reinforcement Learning, Institute of Physics and Mathematics (IPM) monthly seminars on Machine Learning, Summer 2004.
Hierarchical Reinforcement Learning, Distributed AI class (Dr. Majid Nili Ahmadabadi), Spring 2004.
Behavior-based Systems, IPM monthly seminars on Machine Learning, Winter 2004.
A short course on Soft Computing, K.N. Toosi Univ. of Tech., Summer 2002.
Evolving Hidden Markov Models, 4th Iranian Student Conference on Electrical Engineering, 2001.
Distributed Genetic Algorithms, 3rd Iranian Student Conference on Electrical Engineering, 2000.
Several presentations in The First Soft Computing Workshop in K.N. Toosi University of Technology, 2000.
A short course on Evolutionary Algorithms, K.N. Toosi University of Technology, 1999-2000.
Data Compression Methods, Alumni of NODET students, 1998.