Loading...
Search for:
learning
0.011 seconds
Total 1677 records
Cascading randomized weighted majority: A new online ensemble learning algorithm
, Article Intelligent Data Analysis ; Volume 20, Issue 4 , 2016 , Pages 877-889 ; 1088467X (ISSN) ; Beigy, H ; Shaban, A ; Sharif University of Technology
IOS Press
2016
Abstract
With the increasing volume of data, the best approach for learning from this data is to exploit an online learning algorithm. Online ensemble methods take advantage of an ensemble of classifiers to predict labels of data. Prediction with expert advice is a well-studied problem in the online ensemble learning literature. The weighted majority and the randomized weighted majority (RWM) algorithms are two well-known solutions to this problem, aiming to converge to the best expert. Since among some expert, the best one does not necessarily have the minimum error in all regions of data space, defining specific regions and converging to the best expert in each of these regions will lead to a...
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...
Design and Comparison of Memristor Implementation for Different Machine Learning Algorithms
, M.Sc. Thesis Sharif University of Technology ; Bagheri Shouraki, Saeed (Supervisor)
Abstract
The first physical realization of the missing fourth fundamental element of electrical circuits, namely memristor, in 2008 by HP labs triggered an immense amount of research on the capabilities of this element in implementing artificial neurons and artificial brain. In this project we will propose several reinforcement learning-based algorithms that are implemented on a specific memristor-based structure, the memristor crossbar structure. Hence we provide a learning paradigm that resembles the human learning paradigm not only because of the the algorithmic core, which is based on learning from sparse and delayed rewards and penalties, but also because of the hardware over which the...
Application of Semi-Supervised Learning in Image Processing
, M.Sc. Thesis Sharif University of Technology ; Rabiee, Hamidreza (Supervisor)
Abstract
In recent years, the emergence of semi-supervised learning methods has broadened the scope of machine learning, especially for pattern classification. Besides obviating the need for experts to label the data, efficient use of unlabeled data causes a significant improvement in supervised learning methods in many applications. With the advent of statistical learning theory in the late 80's, and the emergence of the concept of regularization, kernel learning has always been in deep concentration. In recent years, semi-supervised kernel learning, which is a combination of the two above-mentioned viewpoints, has been considered greatly.
Large number of dimensions of the input data along with...
Large number of dimensions of the input data along with...
Design and implementation of three different methods for announcing exam grades on the web
, Article 8th IEEE International Conference on Advanced Learning Technologies, ICALT 2008, Santander, 1 July 2008 through 5 July 2008 ; 2008 , Pages 335-337 ; 9780769531670 (ISBN) ; Sharif University of Technology
2008
Abstract
After the emergence of modern technologies in the field of information technologies (IT), virtual learning has attained a new form. The way of announcing exams' grades is an important topic in e-learning. For announcing exams' grades on the web, various methods have been proposed. In this paper, first some common methods for announcing students' grades are reviewed, then three new methods which are named "Virtual Grade", "Steganography Grades", and "Grade HIP" are introduced and the result of implementing these methods for announcing the grades of some courses at the some Iranian universities are provided. Also these methods and their results are analyzed. Finally these three new methods are...
An agent-based architecture with centralized management for a distance learning system
, Article International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007, Sivakasi, Tamil Nadu, 13 December 2007 through 15 December 2007 ; Volume 1 , 2008 , Pages 68-76 ; 0769530508 (ISBN); 9780769530505 (ISBN) ; Nazemi, E ; Sharif University of Technology
2008
Abstract
In this paper we have proposed a multi-agent architecture for an Intelligent Tutoring System using TROPOS methodology. Basic assumptions of constructivist learning have been taken into account in analysis and design activities. Nine types of agents are distinguished in the presented system. We have centralized management in the proposed architecture which is done by an agent called Manager Agent. This strategy of centralized management will result in a more coherent and effective Tutoring System than other systems not using such an agent, since it applies control flow of agents and decreases agents ' useless communications which may cause destructive congestion in system. This text discusses...
Analysis of the Level of Learning in the Research Office of Sharif University of Technology based on Single Loop and Double Loop Learning Models
, M.Sc. Thesis Sharif University of Technology ; Mashayekhi, Ali Naghi (Supervisor)
Abstract
Today the economical and technological success of a nation is based upon the amount of knowledge that is created within that nation. Thus universities, as the main engines for creating knowledge, are held responsible for this matter. Sharif University is one of the top universities in Iran; which is fortunate to have some of the very high quality faculties across nation and has been succesfull so far to attract the highest ranked students for both its undergraduate and graduate programs. Unfortunately, despite its potentials, Sharif University has not reached its desirable place in the world and nation’s ranking of universities according to their research index. This research has thus...
Meta Reinforcement Learning for Domain Generalization
, M.Sc. Thesis Sharif University of Technology ; Rohban, Mohammad Hossein (Supervisor)
Abstract
Deep reinforcement learning has achieved better cumulative rewards than humans in many environments like Atari. One drawback of these methods is their data inefficiency which makes training time-consuming, and in some cases having this amount of data is infeasible. Meta reinforcement learning can use past experiences to enable agents to adapt to new tasks faster and makes neural networks to train in a short amount of time.One of the methods in meta reinforcement learning is inferring tasks which helps exploitation policy to have good performance in new tasks. There’s a need to improve exploration policy as well as exploitation policy by gaining informative transitions about the new task....
Some Model-free Discrete Reinforcement Learning Algorithms
, M.Sc. Thesis Sharif University of Technology ; Daneshgar, Amir (Supervisor)
Abstract
In this thesis, we review some methods related to model-free discrete reinforcement learning and their corresponding algorithms. Our main goal is to present existing methods in an integrated and formal setup, without compromising their mathematical accuracy or comprehensibility. We have done our best to fix the inconsistencies existing in notations and definitions appearing in different areas of the vast literature. We discuss dynamic programming methods, including policy iteration and value iteration and temporal difference methods as well as policy-based methods such as policy gradient, advantage actor-critic, TRPO, and PPO. Among value-based methods, we discuss Q-learning and C51 where we...
Self-Supervised Image Representation Learning
, M.Sc. Thesis Sharif University of Technology ; Kasaei, Shohreh (Supervisor)
Abstract
Self-supervied learning is a method to reduce the need for large labeled datasets in supervised learning. In self-supervised learning, the goal is to design a pretext task that can be trained without any labels. This pretext task results in learning a representation of data that can reduce the need for labels when used for different tasks. In the domain of images, data augmenting transformations which are often a composition of simple transformations such as random cropping and color jitter have been used for the design of pretext tasks. These simple transformations can cause information loss in some datasets which limits the usage of the learned representations for various downstream tasks....
Exploiting structural information of data in active learning
, Article Artificial Intelligence and Soft Computing: Lecture Notes in Computer Science ; Volume 8468 LNAI, Issue PART 2 , 2014 , Pages 796-808 ; Beigy, Hamid ; Haghiri, Siavash ; Sharif University of Technology
Abstract
In recent years, the active learning algorithms have focused on combining correlation criterion and uncertainty criterion for evaluating instances. Although these criteria might be useful, applying these measures on whole input space globally may lead to inefficient selected instances for active learning. The proposed method takes advantage of clustering to partition input space to subspaces. Then it exploits both labeled and unlabeled data locally for selection of instances by using a graph-based active learning. We define a novel utility score for selecting clusters by combining uncertainty criterion, local entropy of clusters and the factor of contribution of each cluster in queries....
Gait analysis of a six-legged walking robot using fuzzy reward reinforcement learning
, Article 13th Iranian Conference on Fuzzy Systems, IFSC 2013 ; August , 2013 , Page(s): 1 - 4 ; ISBN: 9781479912278 ; Khayyat, A. A ; Sharif University of Technology
IEEE Computer Society
2013
Abstract
Free gait becomes necessary in walking robots when they come to walk over discontinuous terrain or face some difficulties in walking. A basic gait generation strategy is presented here using reinforcement learning and fuzzy reward approach. A six-legged (hexapod) robot is implemented using Q-learning algorithm. The learning ability of walking in a hexapod robot is explored considering only the ability of moving its legs and using a fuzzy rewarding system telling whether and how it is moving forward. Results show that the hexapod robot learns to walk using the presented approach properly
A genetic programming-based learning algorithms for pruning cost-sensitive classifiers
, Article International Journal of Computational Intelligence and Applications ; Volume 11, Issue 2 , June , 2012 ; 14690268 (ISSN) ; Beigy, H ; Sharif University of Technology
2012
Abstract
In this paper, we introduce a new hybrid learning algorithm, called DTGP, to construct cost-sensitive classifiers. This algorithm uses a decision tree as its basic classifier and the constructed decision tree will be pruned by a genetic programming algorithm using a fitness function that is sensitive to misclassification costs. The proposed learning algorithm has been examined through six cost-sensitive problems. The experimental results show that the proposed learning algorithm outperforms in comparison to some other known learning algorithms like C4.5 or naïve Bayesian
An incremental spam detection algorithm
, Article 2011 International Symposium on Artificial Intelligence and Signal Processing, AISP 2011, 15 June 2011 through 16 June 2011 ; June , 2011 , Pages 31-36 ; 9781424498345 (ISBN) ; Beigy, H ; Sharif University of Technology
2011
Abstract
The voluminous of the e-mails are spam. Several algorithms are represented for spam detection based on batch learning. In this paper, a new algorithm based on incremental learning is introduced. The algorithm composes new knowledge from new training data with previous knowledge by combining classifiers based on weighted majority voting. The experiment results show that the proposed algorithm outperforms other related incremental algorithms and non-incremental algorithms
Metric learning for semi-supervised clustering using pairwise constraints and the geometrical structure of data
, Article Intelligent Data Analysis ; Volume 13, Issue 6 , 2009 , Pages 887-899 ; 1088467X (ISSN) ; Bagheri Shouraki, S ; Sharif University of Technology
Abstract
Metric learning is a powerful approach for semi-supervised clustering. In this paper, a metric learning method considering both pairwise constraints and the geometrical structure of data is introduced for semi-supervised clustering. At first, a smooth metric is found (based on an optimization problem) using positive constraints as supervisory information. Then, an extension of this method employing both positive and negative constraints is introduced. As opposed to the existing methods, the extended method has the capability of considering both positive and negative constraints while considering the topological structure of data. The proposed metric learning method can improve performance of...
Multi-label learning in the independent label sub-spaces
, Article Pattern Recognition Letters ; Volume 97 , 2017 , Pages 8-12 ; 01678655 (ISSN) ; Kwok, J. T ; Rabiee, H. R ; Sharif University of Technology
Abstract
The objective in multi-label learning problems is simultaneous prediction of many labels for each input instance. During the past years, there were many proposed embedding based approaches to solve this problem by considering label dependencies and decreasing learning and prediction cost. However, compressing the data leads to lose part of information included in label space. The idea in this work is to divide the whole label space to some independent small groups which leads to independent learning and prediction for each small group in the main space, rather than transforming to the compressed space. We use subspace clustering approaches to extract these small partitions such that the...
Integration of handheld NIR and machine learning to “Measure & Monitor” chicken meat authenticity
, Article Food Control ; Volume 112 , 2020 ; Van Kollenburg, G ; Weesepoel, Y ; Van den Doel, A ; Buydens, L ; Jansen, J ; Sharif University of Technology
Elsevier Ltd
2020
Abstract
By combining portable, handheld near-infrared (NIR) spectroscopy with state-of-the-art classification algorithms, we developed a powerful method to test chicken meat authenticity. The research presented shows that it is both possible to discriminate fresh from thawed meat, based on NIR spectra, as well as to correctly classify chicken fillets according to the growth conditions of the chickens with good accuracy. In all cases, the random subspace discriminant ensemble (RSDE) method significantly outperformed other common classification methods such as partial least squares-discriminant analysis (PLS-DA), artificial neural network (ANN) and support vector machine (SVM) with classification...
Real-Time IDS using reinforcement learning
, Article 2008 2nd International Symposium on Intelligent Information Technology Application, IITA 2008, Shanghai, 21 December 2008 through 22 December 2008 ; Volume 2 , January , 2008 , Pages 593-597 ; 9780769534978 (ISBN) ; Bagheri Shouraki, S ; Hosein, K ; Mahdi, D ; Sharif University of Technology
2008
Abstract
In this paper we proposed a new real-time learning method. The engine of this method is a fuzzy-modeling technique which is called ink drop spread (IDS). IDS method has good convergence and is very simple and away from complex formula. The proposed method uses a reinforcement learning approach by an actor-critic system similar to Generalized Approximate Reasoning based Intelligent Control (GARIC) structure to adapt the IDS by delayed reinforcement signals. Our system uses Temporal Difference (TD) learning to model the behavior of useful actions of a control system. It is shown that the system can adapt itself, commencing with random actions. © 2008 IEEE
Automatic learning of action priorities
, Article Proceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing, Marbella, 1 September 2004 through 3 September 2004 ; 2004 , Pages 255-259 ; 0889864586 (ISBN) ; Ghassem Sani, G. R ; IASTED, TCAIETCSC ; Sharif University of Technology
2004
Abstract
Traditional AI planners often suffer from their poor efficiency. There are many choice points in the planning process, but lack of information precludes proper decision. In this paper, we introduce a new method for adding automatic learning capability to a forward planning system. Our idea is based on a dynamic voting algorithm to choose the best action to proceed to the next state. In every planning cycle, applicable actions (i.e. those actions whose preconditions are satisfied in the current world state) vote to, and compete with each other. As a result of this voting, gradually more useful actions are chosen. This idea has been applied to the blocks world domain, and the preliminary...
λ-universe: Introduction and preliminary study
, Article Advances in Neural Networks and Applications ; 2001 , Pages 140-145 ; 9608052262 (ISBN) ; Sharif University of Technology
World Scientific and Engineering Academy and Society
2001
Abstract
Interactions between the members of an imaginary universe, where all the members are adaptive and have learning capability, is simulated numerically by using artificial neural networks. The universe is called λ-universe for brevity. It is shown here that in such a universe, rules governing the behavior of the members might be formed inside the universe by its own members and the randomness which is observed in the behavior of its members is a direct result of the learning capability of the members. Although this is not a simulation of the real universe, some fundamental concepts of astrophysics have been implemented in it