Abstract not found

In this paper we propose a novel gradient algorithm to learn a policy from an expert’s observed behavior assuming that the expert behaves optimally with respect to some unknown reward function of a Markovian Decision Problem. The algorithm’s aim is to find a reward function such that the resulting optimal policy matches well the expert’s observed behavior. The main difficulty is that the mapping from the parameters to policies is both nonsmooth and highly redundant. Resorting to subdifferentials solves the first difficulty, while the second one is overcome by computing natural gradients. We tested the proposed method in two artificial domains and found it to be more reliable and efficient than some previous methods. 1

In this study, we give a brief overview of search strategy adaptation in evolutionary computation. The

Abstract — Regularization is an essential technique to improve generalization of neural networks. Traditionally, regularization is conduced by including an additional term in the cost function of a learning algorithm. One main drawback of these regularization techniques is that a hyperparameter that determines to which extension the regularization in¤uences the learning algorithm must be determined beforehand. This paper addresses the neural network regularization problem from a multi-objective optimization point of view. During the optimization, both structure and parameters of the neural network will be optimized. A slightly modi£ed version of two multi-objective optimization algorithms, the dynamic weighted aggregation (DWA) method and the elitist non-dominated sorting genetic algorithm (NSGA-II) are used and compared. An evolutionary multi-objective approach to neural network regularization has a number of advantages compared to the traditional methods. First, a number of models with a spectrum of model complexity can be obtained in one optimization run instead of only one single solution. Second, an ef£cient new regularization term can be introduced, which is not applicable to gradient-based learning algorithms. As a natural by-product of the multi-objective optimization approach to neural network regularization, neural network ensembles can be easily constructed using the obtained networks with different levels of model complexity. Thus, the model complexity of the ensemble can be adjusted by adjusting the weight of each member network in the ensemble. Simulations are carried out on a test function to illustrate the feasibility of the proposed ideas. I.

There exist many ideas and assumptions concerning the development and meaning of modularity in biological and technical neural systems. Nevertheless, this wide field is far from being understood; quantitative simulations and investigations are rare. In our contribution, we empirically study the development of connectionist models in the context of the evolution of artificial neural networks for highly modular problems. We define two measures for the degree of modularity and monitor their values during the evolutionary process. We identify two different reasons for the development of modular structures: the modularity of the task is reflected by the modularity of the adapted structure and the demand for fast learning structures increases the selective pressure towards modularity. However, learning can also counterbalance some imperfection of the underlying structure.

This paper presents a time series forecasting methodology and applies it to generate one--step-- ahead predictions for the daily foreign exchange spot rates. The methodology draws from the disciplines of chaotic time series analysis, clustering, artificial neural networks and evolutionary computation. In brief, clustering is applied to identify neighborhoods in the reconstructed state space of the system; and subsequently neural networks are trained to model the dynamics of each neighborhood separately. The results obtained through this approach are promising.

We describe the use of ensemble methods to build proper models for time series prediction. Our approach extends the classical ensemble methods for neural networks by using several different model architectures. We further suggest an iterated prediction procedure to select the final ensemble members.

The main focus of the optimization of artificial neural networks has been the design of a problem dependent network structure in order to reduce the model complexity and to minimize the model error. Driven by a concrete application we identify in this paper another desirable property of neural networks -- the ability of the network to efficiently solve related problems denoted as a class of problems. In a more theoretical framework the aim is to develop neural networks for adaptability -- networks that learn (during evolution) to learn (during operation) . Evolutionary algorithms have turned out to be a robust method for the optimization of neural networks. As this process is time consuming, it is therefore also from the perspective of efficiency desirable to design structures that are applicable to many related problems. In this paper, two different approaches to solve this problem are studied, called ensemble method and generation method. We empirically show that an averaged Lamarcki...

One major idea in structured prediction is to assume that the predictor computes its output by finding the maximum of a score function. The training of such a predictor can then be cast as the problem of finding weights of the score function so that the output of the predictor on the inputs matches the corresponding structured labels on the training set. A similar problem is studied in inverse reinforcement learning (IRL) where one is given an environment and a set of trajectories and the problem is to find a reward function such that an agent acting optimally with respect to the reward function would follow trajectories that match those in the training set. In this paper we show how IRL algorithms can be applied to structured prediction, in particular to parser training. We present a number of recent incremental IRL algorithms in a unified framework and map them to parser training algorithms. This allows us to recover some existing parser training algorithms, as well as to obtain a new one. The resulting algorithms are compared in terms of their sensitivity to the choice of various parameters and generalization ability on the Penn Treebank WSJ corpus.

We like to present a method to build ensemble models based on an extended cross-validation approach. The cross-validation puts several model classes in a tournament and selects the best performing model with respect to the validation set. This leads to a model selection strategy and an estimation of the expected modelling error.