|
Research Interests:
- Statistical Machine Learning
- Graphical Models
- Causality Detection
- Optimization
- Deep Learning
- Anomaly Detection
- Active Learning
|
|
Education:
- PhD student in Intelligent Systems Program,
University of Pittsburgh, Pittsburgh, PA,
2011-present.
- MSc in Intelligent Systems Program,
University of Pittsburgh, Pittsburgh, PA,
2011-2013.
- MSc in Robotic & Artificial Intelligence,
University
of Tehran (UT), Tehran, Iran, 2001- 2004
- BSc in Computer Engineering-Software,
Iran University of
Science and Technology (IUST),Tehran, Iran,
1997-2001
|
|
Publications:
- Mahdi Pakdaman Naeini, G. F. Cooper. "Binary Classifier Calibration using an Ensemble of Near Isotonic Regression Models”, IEEE Internation Conference on Data Mining (ICDM), Barcelona, Spain, December 2016.
- Mahdi Pakdaman Naeini, G. F. Cooper. "Obtaining Accurate Probabilities using an Ensemble of Linear Trend Estimation”, SIAM Data Mining (SDM), Miami, FL, May 2016.
- Mahdi Pakdaman Naeini, G. F. Cooper, M. Hauskrecht. "Obtaining Calibrated Probabilities using Bayesian Binning",
Association for the Advancement of Artificial Intelligence (AAAI), Austin, TX, January 2015 [code]
- Mahdi Pakdaman Naeini, G. F. Cooper, M. Hauskrecht. "Binary Classifier Calibration: A Bayesian Non-Parametric Approach",
SIAM Data Mining (SDM), Vancouver, Canada, May 2015.
- Mahdi Pakdaman Naeini, I. Batal, Z. Liu, C. Hong, and M. Hauskrecht. "An Optimization- based Framework to Learn Conditional Random Fields for Multi-label Classification". SIAM Data Mining (SDM), Philadelphia, PA, April 2014.
- A. Saluja, Mahdi Pakdaman Naeini, D. Piao, and A.P. Parikh. "Infinite Mixed Member- ship Matrix Factorization". IEEE 13th International Conference on Data Mining (ICDM) Workshops, Dallas, TX, December 2013.
- Mahdi Pakdaman Naeini, B. Araabi, B. Moshiri, M. Sadeghi. "Learning by abstraction: Hierarchical classification model using evidential theoretic approach and Bayesian ensemble model". Neurocomputing journal, 2013.
- H. B. Hashemi, N. Yazdani, A. Shakery, Mahdi Pakdaman Naeini, "Application of Ensemble Models in Web Ranking",
Fifth International Symposium on Telecommunications (IST), 2010.[PDF]
- Mahdi Pakdaman Naeini, H. Taromian, and Homa Baradaran Hashemi, Stock Market Vaule Prediction using Neural Networks,
International Conference on Computer Information Systems and Industrial Management Applications (CISIM), 2010.[PDF]
- Mahdi Pakdaman Naeini, Behzad Moshiri, Kaveh Kavousi. "Protein Fold Recognition
using a bagging ensemble of SVM classifiers", 8th APIS Conference, University of the Ryukyus, Okinawa,
Japan 2009. [PDF]
- H. B. Hashemi, A. Shakery, Mahdi Pakdaman Naeini, "Protein Fold Pattern Recognition Using Bayesian Ensemble of RBF Neural
Networks", International Conference of Soft Computing and Pattern Recognition, Malaysia
2009. [PDF]
- Mahdi Pakdaman Naeini, Alireza Alemi , Caro Lucas.
"Intelligent Multi-Agent Electronic Banking Design and Implementation",
Electronic Commerce, Necessities and Approaches IT Conference, Isfahan, Iran, 2004.
|
|
Teaching Experiences:
- Advanced Algorithm Analysis and Design (Payam Noor university )
- Introduction to Algorithm (Azad University of Parand)
- Software Engineering (Azad University of Parand)
- Advanced Programming and Data Structures (Azad University of Parand)
- Artificial Intelligence (Azad University of Parand)
- Data Mining (Azad University of Parand)
- Theory of Languages and Machines (Azad University of Parand)
|
|
Presentation and Talks:
-
Mahdi Pakdaman Naeini, "Introduction to Copula Functions",
Advanced Machine Learning Seminar, Sep 2011.
-
Mahdi Pakdaman Naeini, "Introduction to Kernel Methods",
Automated Fraud Detection workshop IPM, 08 August 2010.
-
Mahdi Pakdaman Naeini, "Protein Domain Assignment using computational approaches",
IPM-FAST IR workshop on computational biology, 27-29 Jan 2010.
-
Mahdi Pakdaman Naeini, "Neural Networks",
Invited talk in Bioinformatic Course, Institute of Biophysics and Biochemistry(IBB), University of Tehran, Iran, December 2008.
-
Mahdi Pakdaman Naeini, "Hidden Markov Model and its application in Bioinformatics",
Bioinformatics Group meeting, ECE Department, University of Tehran, Iran, October 2008.
-
Mahdi Pakdaman Naeini, "Theory of Learning and Support Vector Machines",
Data Mining Seminar, ECE Department, University of Tehran, Iran, December 2007.
-
Caro Lucas, Mahdi Pakdaman Naeini, "Mobile Banking",
Workshop on E-Banking, IT conference, University of Tehran, Iran, 2003.
-
Caro Lucas, Mahdi Pakdaman Naeini, "Load Risk
Assessment System", Workshop on E-Banking and
E-negotiation, First International IT conference,
Hamedan, Iran, 2003.
|
|
Thesis:
- MS thesis: "Design and Implementation of an
Intelligent Decision Support system for Credit Risk
Assessment Using Soft Computing Methods" under
supervision of Prof. Caro Lucas, University of
Tehran 2003-2004.
- BS thesis:
"Linux Administration Toolkit" under supervision of
Dr. Sharifi 2000-2001.
|
|
Useful Links:
|
|