Showing papers on "Active learning (machine learning) published in 1997"

Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review]

Abstract: Interestingly, neuro fuzzy and soft computing a computational approach to learning and machine intelligence that you really wait for now is coming. It's significant to wait for the representative and beneficial books to read. Every book that is provided in better way and utterance will be expected by many peoples. Even you are a good reader or not, feeling to read this book will always appear when you find it. But, when you feel hard to find it as yours, what to do? Borrow to your friends and don't know when to give back it to her or him.

Selection of relevant features and examples in machine

Abstract: In this survey, we review work in machine learning on methods for handling data sets containing large amounts of irrelevant information. We focus on two key issues: the problem of selecting relevant features, and the problem of selecting relevant examples. We describe the advances that have been made on these topics in both empirical and theoretical work in machine learning, and we present a general framework that we use to compare different methods. We close with some challenges for future work in this area. @ 1997 Elsevier Science B.V.

Machine-Learning Research

Abstract: Machine-learning research has been making great progress in many directions. This article summarizes four of these directions and discusses some current open problems. The four directions are (1) the improvement of classification accuracy by learning ensembles of classifiers, (2) methods for scaling up supervised learning algorithms, (3) reinforcement learning, and (4) the learning of complex stochastic models.

Selective Sampling Using the Query by Committee Algorithm

Abstract: We analyze the “query by committee” algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of perceptrons.

Reinforcement Learning with Hierarchies of Machines

Abstract: We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This allows for the use of prior knowledge to reduce the search space and provides a framework in which knowledge can be transferred across problems and in which component solutions can be recombined to solve larger and more complicated problems. Our approach can be seen as providing a link between reinforcement learning and "behavior-based" or "teleo-reactive" approaches to control. We present provably convergent algorithms for problem-solving and learning with hierarchical machines and demonstrate their effectiveness on a problem with several thousand states.

Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF

Abstract: Current inductive machine learning algorithms typically use greedy search with limited lookahead. This prevents them to detect significant conditional dependencies between the attributes that describe training objects. Instead of myopic impurity functions and lookahead, we propose to use RELIEFF, an extension of RELIEF developed by Kira and Rendell l10, 11r, for heuristic guidance of inductive learning algorithms. We have reimplemented Assistant, a system for top down induction of decision trees, using RELIEFF as an estimator of attributes at each selection step. The algorithm is tested on several artificial and several real world problems and the results are compared with some other well known machine learning algorithms. Excellent results on artificial data sets and two real world problems show the advantage of the presented approach to inductive learning.

Robot Learning From Demonstration

Abstract: The goal of robot learning from demonstration is to have a robot learn from watching a demonstration of the task to be performed. In our approach to learning from demonstration the robot learns a reward function from the demonstration and a task model from repeated attempts to perform the task. A policy is computed based on the learned reward function and task model. Lessons learned from an implementation on an anthropomorphic robot arm using a pendulum swing up task include 1) simply mimicking demonstrated motions is not adequate to perform this task, 2) a task planner can use a learned model and reward function to compute an appropriate policy, 3) this modelbased planning process supports rapid learning, 4) both parametric and nonparametric models can be learned and used, and 5) incorporating a task level direct learning component, which is non-model-based, in addition to the model-based planner, is useful in compensating for structural modeling errors and slow model learning.

Locally weighted learning for control

Abstract: Lazy learning methods provide useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of complex systems. This paper surveys ways in which locally weighted learning, a type of lazy learning, has been applied by us to control tasks. We explain various forms that control tasks can take, and how this affects the choice of learning paradigm. The discussion section explores the interesting impact that explicitly remembering all previous experiences has on the problem of learning to control.

Reinforcement learning in the multi-robot domain

Abstract: This paper describes a formulation of reinforcement learning that enables learning in noisy, dynamic environments such as in the complex concurrent multi-robot learning domain. The methodology involves minimizing the learning space through the use of behaviors and conditions, and dealing with the credit assignment problem through shaped reinforcement in the form of heterogeneous reinforcement functions and progress estimators. We experimentally validate the approach on a group of four mobile robots learning a foraging task.

A Theory of Learning and Generalization

Abstract: From the Publisher: How does it differ from first edition? Includes new material on: * support vector machines (SVM's), * fat shattering dimensions * applications to neural network learning, * learning with dependent samples generated by beta-mixing process, * connections between system identification and learning theory * probabilistic solution of "intractable" problems in robust control and matrix theory using randomised algorithms. In addition, solutions to some open problems posed in the first edition are included, and new open problems are added. The author is a respected authority in the field of control and systems theory. This new edition, with substantial new material, takes account of important new developments in the theory of learning. It also deals extensively with the theory of learning control systems, which has now reached a level of maturity comparable to that of learning of neural networks. The book is written in a manner that would suit self-study and contains comprehensive references. The chapters are also written to be as autonomous as possible and contain updated open problems to enhance further research and self-study.

Automatic Learning Techniques in Power Systems

Abstract: From the Publisher: Automatic Learning Techniques in Power Systems is dedicated to the practical application of automatic learning to power systems Power systems to which automatic learning can be applied are screened and the complementary aspects of automatic learning, with respect to analytical methods and numerical simulation, are investigated This book presents a representative subset of automatic learning methods - basic and more sophisticated ones - available from statistics (both classical and modern), and from artificial intelligence (both hard and soft computing) The text also discusses appropriate methodologies for combining these methods to make the best use of available data in the context of real-life problems Automatic Learning Techniques in Power Systems is a useful reference source for professionals and researchers developing automatic learning systems in the electrical power field

Learning When Negative Examples Abound

Abstract: Existing concept learning systems can fail when the negative examples heavily outnumber the positive examples. The paper discusses one essential trouble brought about by imbalanced training sets and presents a learning algorithm addressing this issue. The experiments (with synthetic and real-world data) focus on 2-class problems with examples described with binary and continuous attributes.

Layered learning in multiagent systems

Abstract: Multi-agent systems in complex, real-time domains require agents to act effectively both autonomously and as part of a team. This dissertation addresses multi-agent systems consisting of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. Because of the inherent complexity of this type of multi-agent system, this thesis investigates the use of machine learning within multi-agent systems. The dissertation makes four main contributions to the fields of Machine Learning and Multi-Agent Systems. First, the thesis defines a team member agent architecture within which a flexible team structure is presented, allowing agents to decompose the task space into flexible roles and allowing them to smoothly switch roles while acting. Team organization is achieved by the introduction of a locker-room agreement as a collection of conventions followed by all team members. It defines agent roles, team formations, and pre-compiled multi-agent plans. In addition, the team member agent architecture includes a communication paradigm for domains with single-channel, low-bandwidth, unreliable communication. The communication paradigm facilitates team coordination while being robust to lost messages and active interference from opponents. Second, the thesis introduces layered learning, a general-purpose machine learning paradigm for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable. Given a hierarchical task decomposition, layered learning allows for learning at each level of the hierarchy, with learning at each level directly affecting learning at the next higher level. Third, the thesis introduces a new multi-agent reinforcement learning algorithm, namely team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL is designed for domains in which agents cannot necessarily observe the state changes when other team members act. It exploits local, action-dependent features to aggressively generalize its input representation for learning and partitions the task among the agents, allowing them to simultaneously learn collaborative policies by observing the long-term effects of their actions. Fourth, the thesis contributes a fully functioning multi-agent system that incorporates learning in a real-time, noisy domain with teammates and adversaries. Detailed algorithmic descriptions of the agents' behaviors as well as their source code are included in the thesis. Empirical results validate all four contributions within the simulated robotic soccer domain. The generality of the contributions is verified by applying them to the real robotic soccer, and network routing domains. Ultimately, this dissertation demonstrates that by learning portions of their cognitive processes, selectively communicating, and coordinating their behaviors via common knowledge, a group of independent agents can work towards a common goal in a complex, real-time, noisy, collaborative, and adversarial environment.

On the Accuracy of Meta-learning for Scalable Data Mining

Abstract: In this paper, we describe a general approach to scaling data mining applications that we have come to call meta-learning. Meta-Learning refers to a general strategy that seeks to learn how to combine a number of separate learning processes in an intelligent fashion. We desire a meta-learning architecture that exhibits two key behaviors. First, the meta-learning strategy must produce an accurate final classification system. This means that a meta-learning architecture must produce a final outcome that is at least as accurate as a conventional learning algorithm applied to all available data. Second, it must be fast, relative to an individual sequential learning algorithm when applied to massive databases of examples, and operate in a reasonable amount of time. This paper focussed primarily on issues related to the accuracy and efficacy of meta-learning as a general strategy. A number of empirical results are presented demonstrating that meta-learning is technically feasible in wide-area, network computing environments.

Active Learning with Committees for Text Categorization

Abstract: In many real-world domains, supervised learning requires a large number of training examples. In this paper, we describe an active learning method that uses a committee of learners to reduce the number of training examples required for learning. Our approach is similar to the Query by Committee framework, where disagreement among the committee members on the predicted label for the input part of the example is used to signal the need for knowing the actual value of the label. Our experiments are conducted in the text categorization domain, which is characterized by a large number of features, many of which are irrelevant. We report here on experiments using a committee of Winnowbased learners and demonstrate that this approach can reduce the number of labeled training examples required over that used by a single Winnow learner by l-2 orders of magnitude. 1. Hntroduction

CHILD: A First Step Towards Continual Learning

Abstract: Continual learning is the constant development of increasingly complex behaviors; the process of building more complicated skills on top of those already developed. A continual-learning agent should therefore learn incrementally and hierarchically. This paper describes CHILD, an agent capable of Continual, Hierarchical, Incremental Learning and Development. CHILD can quickly solve complicated non-Markovian reinforcement-learning tasks and can then transfer its skills to similar but even more complicated tasks, learning these faster still.

Tolerating concept and sampling shift in lazy learning using prediction error context switching

Abstract: In their unmodified form, lazy-learning algorithms may have difficulty learning and tracking time-varying input/output function maps such as those that occur in concept shift. Extensions of these algorithms, such as Time-Windowed forgetting (TWF), can permit learning of time-varying mappings by deleting older exemplars, but have decreased classification accuracy when the input-space sampling distribution of the learning set is time-varying. Additionally, TWF suffers from lower asymptotic classification accuracy than equivalent non-forgetting algorithms when the input sampling distributions are stationary. Other shift-sensitive algorithms, such as Locally-Weighted forgetting (LWF) avoid the negative effects of time-varying sampling distributions, but still have lower asymptotic classification in non-varying cases. We introduce Prediction Error Context Switching (PECS) which allows lazy-learning algorithms to have good classification accuracy in conditions having a time-varying function mapping and input sampling distributions, while still maintaining their asymptotic classification accuracy in static tasks. PECS works by selecting and re-activating previously stored instances based on their most recent consistency record. The classification accuracy and active learning set sizes for the above algorithms are compared in a set of learning tasks that illustrate the differing time-varying conditions described above. The results show that the PECS algorithm has the best overall classification accuracy over these differing time-varying conditions, while still having asymptotic classification accuracy competitive with unmodified lazy-learners intended for static environments.

Machine Learning by Function Decomposition

Abstract: We present a new machine learning method that, given a set of training examples, induces a definition of the target concept in terms of a hierarchy of intermediate concepts and their definitions. This effectively decomposes the problem into smaller, less complex problems. The method is inspired by the Boolean function decomposition approach to the design of digital circuits. To cope with high time complexity of finding an optimal decomposition, we propose a suboptimal heuristic algorithm. The method, implemented in program HINT (HIerarchy Induction Tool), is experimentally evaluated using a set of artificial and real-world learning problems. It is shown that the method performs well both in terms of classification accuracy and discovery of meaningful concept hierarchies.

Lazy incremental learning of control knowledge for efficiently obtaining quality plans

Abstract: General-purpose generative planners use domain-independent search heuristics to generate solutions for problems in a variety of domains. However, in some situations these heuristics force the planner to perform inefficiently or obtain solutions of poor quality. Learning from experience can help to identify the particular situations for which the domain-independent heuristics need to be overridden. Most of the past learning approaches are fully deductive and eagerly acquire correct control knowledge from a necessarily complete domain theory and a few examples to focus their scope. These learning strategies are hard to generalize in the case of nonlinear planning, where it is difficult to capture correct explanations of the interactions among goals, multiple planning operator choices, and situational data. In this article, we present a lazy learning method that combines a deductive and an inductive strategy to efficiently learn control knowledge incrementally with experience. We present hamlet, a system we developed that learns control knowledge to improve both search efficiency and the quality of the solutions generated by a nonlinear planner, namely prodigy4.0. We have identified three lazy aspects of our approach from which we believe hamlet greatly benefits: lazy explanation of successes, incremental refinement of acquired knowledge, and lazy learning to override only the default behavior of the problem solver. We show empirical results that support the effectiveness of this overall lazy learning approach, in terms of improving the efficiency of the problem solver and the quality of the solutions produced.

Multi-stage genetic fuzzy systems based on the iterative rule learning approach

Abstract: Genetic algorithms (GAs) represent a class of adaptive search techniques inspired by natural evolution mechanisms The search properties of GAs make them suitable to be used in machine learning processes and for developing fuzzy systems, the so-called genetic fuzzy systems (GFSs) In this contribution, we discuss genetics-based machine learning processes presenting the iterative rule learning approach, and a special kind of GFS, a multi-stage GFS based on the iterative rule learning approach, by learning from examples

Explanation-Based Learning and Reinforcement Learning: A Unified View

Abstract: In speedup-learning problems, where full descriptions of operators are known, both explanation-based learning (EBL) and reinforcement learning (RL) methods can be applied. This paper shows that both methods involve fundamentally the same process of propagating information backward from the goal toward the starting state. Most RL methods perform this propagation on a state-by-state basis, while EBL methods compute the weakest preconditions of operators, and hence, perform this propagation on a region-by-region basis. Barto, Bradtke, and Singh (1995) have observed that many algorithms for reinforcement learning can be viewed as asynchronous dynamic programming. Based on this observation, this paper shows how to develop dynamic programming versions of EBL, which we call region-based dynamic programming or Explanation-Based Reinforcement Learning (EBRL). The paper compares batch and online versions of EBRL to batch and online versions of point-based dynamic programming and to standard EBL. The results show that region-based dynamic programming combines the strengths of EBL (fast learning and the ability to scale to large state spaces) with the strengths of reinforcement learning algorithms (learning of optimal policies). Results are shown in chess endgames and in synthetic maze tasks.

Multiresolution learning paradigm and signal prediction

Abstract: Current neural network learning processes, regardless of the learning algorithm and preprocessing used, are sometimes inadequate for difficult problems. We present a new learning concept and paradigm for neural networks, called multiresolution learning, based on multiresolution analysis in wavelet theory. The multiresolution learning paradigm can significantly improve the generalization performance of neural networks.

System and method for combining multiple learning agents to produce a prediction method

Abstract: System and method for improving the performance of learning agents such as neural networks, genetic algorithms and decision trees that derive prediction methods from a training set of data. In part of the method, a population of learning agents of different classes is trained on the data set, each agent producing in response a prediction method based on the agent's input representation. Feature combinations are extracted from the prediction methods produced by the learning agents. The input representations of the learning agents are then modified by including therein a feature combination extracted from another learning agent. In another part of a method, the parameter values of the learning agents are changed to improve the accuracy of the prediction method. A fitness measure is determined for each learning agent based on the prediction method the agent produces. Parameter values of a learning agent are then selected based on the agent's fitness measure. Variation is introduced into the selected parameter values, and another learning agent of the same class is defined using the varied parameter values. The learning agents are then again trained on the data set to cause a learning agent to produce a prediction method based on the derived feature combinations and varied parameter values.

Efficient reinforcement learning: model-based Acrobot control

Abstract: Several methods have been proposed in the reinforcement learning literature for learning optimal policies for sequential decision tasks. Q-learning is a model-free algorithm that has previously been applied to the Acrobot, a two-link arm with a single actuator at the elbow that learns to swing its free endpoint above a target height. However, applying Q-learning to a real Acrobot may be impractical due to the large number of required movements of the real robot as the controller learns. This paper explores the planning speed and data efficiency of explicitly learning models, as well as using heuristic knowledge to aid the search for solutions and reduce the amount of data required from the real robot.

Learning Generic Mechanisms for Innovative Strategies in Adaptive Design.

Abstract: Like domain concepts, strategic concepts pertain to objects and relationships in a class of domains, but unlike domain concepts, they also enable new strategies for solving a class of problems. Generic teleological mechanisms (GTMs) are a class of strategic concepts especially useful in adaptive design. GTMs, such as cascading, feedback, and feedforward, are abstract functional and causal patterns that lead to adaptation strategies for innovative design. We adopt a task-directed approach to learning and describe a model-based method for learning GTMs from design examples. Given a design that contains a pattern previously unknown to the designer and a similar and related design that does not, the method abstracts, indexes, and stores the partern for potential reuse. Pattern abstraction is enabled by structure-behavior-function models that represent functional, causal, topological, and compositional knowledge of device designs.

Symbolic visual learning

Abstract: 1. The Visual Learning Problem 2. MULTI-HASH: Learning Object Attributes and Hash Tables for Fast 3D Object Recognition 3. Learning Control Strategies for Object Recognition 4. PADO: A New Learning Architecture for Object Recognition 5. Learning Organization Hierarchies of Large Modelbases for Fast Recognition 6. Application of Machine Learning in Function-Based Recognition 7. Learning a Visual Model and an Image Processing Strategy from a Series of Silhouette Images on MIRACLE-IV 8. Assembly Plan from Observation 9. Visual Event Perception 10. A Knowledge Framework for Seeing and Learning 11. Explanation Based Learning for Mobile Robot Perception 12. Navigation with Landmarks: Computing Goal Locations from Place Codes

Machine learning techniques to make computers easier to use

Abstract: Identifying user-dependent information that can be automatically collected helps build a user model by which (1) to predict what the user wants to do next and (2) to do relevant preprocessing Such information is often relational and is best represented by a set of directed graphs A machine learning technique called graph-based induction (GUI) efficiently extracts regularities from such data, based on which a user-adaptive interface is built that can predict the next command, generate scripts and prefetch files in a multi task environment The heart of GBI is pairwise chunking The paper shows how this simple mechanism applies to the top down induction of decision trees for nested attribute representation as well as finding frequently occurring patterns in a graph The results clearly shows that the dependency analysis of computational processes activated by the user commands which is made possible by GBI is indeed useful to build a behavior model and increase prediction accuracy

Agents Learning about Agents: A Framework and Analysis

Abstract: We provide a framework for the study of learning in certain types of multi-agent systems (MAS), that divides an agent’s knowledge about others into different utypes’. We use concepts from computational learning theory to calculate the relative sample complexities of learning the different types of knowledge, given either a supervised or a reinforcement learning algorithm. These results apply only for the learning of a fixed target function, which would probably not exist if the other agents are also learning. We then show how a changing target function affects the learning behaviors of the/agents, and how to determine the advantages of having lower sample complexity. Our results can be used by a designer of a learning agent in a MAS to determine which knowledge he should put into the agent and which knowledge should be learned by the agent.