Search

This paper proposes the implementation of fuzzy motion control based on reinforcement learning (RL) and Lagrange polynomial interpolation (LPI) for gait synthesis of biped robots. First, the procedure of a walking gait is redefined into three states, and the parameters of this designed walking gait are determined. Then, the machine learning approach applied to adjusting the walking parameters is policy gradient RL (PGRL), which can execute real-time performance and directly modify the policy without calculating the dynamic function. Given a parameterized walking motion designed for biped robots, the PGRL algorithm automatically searches the set of possible parameters and finds the fastest possible walking motion. The reward function mainly considered is first the walking speed, which can be estimated from the vision system. However, the experiment illustrates that there are some stability problems in this kind of learning process. To solve these problems, the desired zero moment point trajectory is added to the reward function. The results show that the robot not only has more stable walking but also increases its walking speed after learning. This is more effective and attractive than manual trial-and-error tuning. LPI, moreover, is employed to transform the existing motions to the motion which has a revised angle determined by the fuzzy motion controller. Then, the biped robot can continuously walk in any desired direction through this fuzzy motion control. Finally, the fuzzy-based gait synthesis control is demonstrated by tasks and point- and line-target tracking. The experiments show the feasibility and effectiveness of gait learning with PGRL and the practicability of the proposed fuzzy motion control scheme. [ABSTRACT FROM AUTHOR]

Abstract-This paper presents a new algorithm, called adaptive merging and growing algorithm (AMGA), in designing artificial neural networks (ANNs). This algorithm merges and adds hidden neurons during the training process of ANNs. The merge operation introduced in AMGA is a kind of a mixed mode operation, which is equivalent to pruning two neurons and adding one neuron. Unlike most previous studies, AMGA puts emphasis on autonomous functioning in the design process of ANNs. This is the main reason why AGMA uses an adaptive strategy merges or adds hidden neurons based on the learning ability of hidden neurons or the training progress of ANNs. In order to reduce the amout of retraining after modifying ANN architectures, AGMA prunes hidden neurons by merging correlated hidden neurons and adds hidden neurons by splitting existing hidden neurons. The proposed AMGA has been tested on a number of benchmark problems in machine learning and ANNs, including breast cancer, Australian credit card assessment, and diabetes, gene, glass, heart, iris and thyroid problems. The experimental results show that AMGA can design compact ANN architectures with good generalization ability compared to other algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we propose two cooperative ensemble learning algorithms, i.e., NegBagg and NegBoost, for designing neural network (NN) ensembles. The proposed algorithms incrementally train different individual NNs in an ensemble using the negative correlation learning algorithm. Bagging and boosting algorithms are used in NegBagg and NegBoost, respectively, to create different training sets for different NNs in the ensemble. The idea behind using negative correlation learning in conjunction with the bagging/boosting algorithm is to facilitate interaction and cooperation among NNs during their training. Both NegBagg and NegBoost use a constructive approach to automatically determine the number of hidden neurons for NNs. NegBoost also uses the constructive approach to automatically determine the number of NNs for the ensemble. The two algorithms have been tested on a number of benchmark problems in machine learning and NNs, including Australian credit card assessment, breast cancer, diabetes, glass, heart disease, letter recognition, satellite, soybean, and waveform problems. The experimental results show that NegBagg and NegBoost require a small number of training epochs to produce compact NN ensembles with good generalization. [ABSTRACT FROM AUTHOR]

An NNC-Tree is a decision tree (DT) with each nonterminal node containing a nearest neighbor classifier (NNC). Compared with the conventional axis-parallel DTs (APDTs), the NNC-Trees can be more efficient, because the decision boundary made by an NNC is more complex than an axis- parallel hyperplane. Compared with single-layer NNCs, the NNC-Trees can classify given data in a hierarchical structure that is often useful for many applications. This paper proposes an algorithm for inducing NNC-Trees based on the R4-rule, which was proposed by the author for finding the smallest nearest neighbor based multilayer perceptrons (NN-MLPs). There are mainly two contributions here. 1) A heuristic but effective method is given to define the teacher signals (group labels) for the data assigned to each nonterminal node. 2) The R4-rule is modified so that an NNC with proper size can be designed automatically in each nonterminal node. Experiments with several public databases show that the proposed algorithm can produce NNC-Trees effectively and efficiently. [ABSTRACT FROM AUTHOR]

The process of learning the behavior of a given pro- gram by using machine-learning techniques (based on system-call audit data) is effective to detect intrusions. Rule learning, neural networks, statistics, and hidden Markov models (HMMs) are some of the kinds of representative methods for intrusion detection. Among them, neural networks are known for good performance in learning system-call sequences. In order to apply this knowledge to real-world problems successfully, it is important to determine the structures and weights of these call sequences. However, finding the appropriate structures requires very long time periods be- cause there are no suitable analytical solutions. In this paper, a novel intrusion-detection technique based on evolutionary neural networks (ENNs) is proposed. One advantage of using ENNs is that it takes less time to obtain superior neural networks than when using conventional approaches. This is because they discover the structures and weights of the neural networks simultaneously. Experimental results with the 1999 Defense Advanced Research Projects Agency (DARPA) Intrusion Detection Evaluation (IDEVAL) data confirm that ENNs are promising tools for intrusion detection. [ABSTRACT FROM AUTHOR]

There are numerous combinations of neural networks (NNs) and evolutionary algorithms (EAs) used in classification problems. EAs have been used to train the networks, design their architecture, and select feature subsets. However, most of these combinations have been tested on only a few data sets and many comparisons are done inappropriately measuring the performance on training data or without using proper statistical tests to support the conclusions. This paper presents an empirical evaluation of eight combinations of EAs and NNs on 15 public-domain and artificial data sets. Our objective is to identify the methods that consistently produce accurate classifiers that generalize well. In most cases, the combinations of EAs and NNs perform equally well on the data sets we tried and were not more accurate than hand-designed neural networks trained with simple backpropagation. [ABSTRACT FROM AUTHOR]