Search

This paper develops a novel insight and procedure that includes a variety of algorithms for finding the best solution in a structured multi-agent system with internal communications and a global purpose. In other words, it finds the optimal communication structure among agents and the optimal policy in this structure. First, a unique reinforcement learning algorithm is proposed to find the optimal policy of each agent in a fixed structure with non-linear function approximators like artificial neural networks (ANN) and with eligibility traces. Secondly, a mechanism is presented to perform self-organization based on the information of the learned policy. Finally, an algorithm that can discover an appropriate inter-structure mapping and then can transfer the previous knowledge to the new structure is developed, which increases the speed of the learning in this new environment after self-organization. This paper is one of the first works that analyzes the problem fully theoretically and devises some algorithms to find the best solution. We use a simplified version of the distributed task allocation problem (DTAP) as our case study. The experimental results verify the stability of our approach and show the high speed of finding the optimal solution as a result of using transfer learning. [ABSTRACT FROM AUTHOR]

[Display omitted] • We propose the TWD-SFNN model to optimize the hidden layer nodes of neural network. • TWD-SFNN adopts three-way decisions to determine the number of hidden layer nodes. • We analyze the space and time complexities of TWD-SFNN. • TWD-SFNN has a more compact network structure than SFNN using empirical formulas. • TWD-SFNN has a better generalization performance than other classification models. Neural networks have a strong self-learning ability and a wide range of applications. The current neural network models mainly determine the number of hidden layer nodes using empirical formulas, which lack theoretical guidance and can easily lead to poor learning performance. To improve the performance of the neural network model, inspired by the three-way decisions method, this paper proposes a model called three-way decisions with a single hidden layer feedforward neural network (TWD-SFNN). TWD-SFNN adopts three-way decisions to find the number of hidden layer nodes for a neural network in a dynamic way. TWD-SFNN has three key issues: discretizing the datasets, adjusting the learning process of the network, and evaluating the learning results of the network. TWD-SFNN adopts the k-means++ algorithm to discretize the datasets, employs the Adam algorithm to adjust the learning process of the network, and uses a confusion matrix to evaluate the learning results of the network. Therefore, the topological structure of the neural network is obtained. The experimental results verify that the network structure of TWD-SFNN is more compact than those of the SFNN models that use empirical formulas to determine the number of hidden layer nodes, and the generalization ability of TWD-SFNN is better than the state-of-the-art classification models. [ABSTRACT FROM AUTHOR]

This paper presents an interpretable neural system—termed Evolving Long-term Cognitive Network—for pattern classification. The proposed model was inspired by Fuzzy Cognitive Maps, which are interpretable recurrent neural networks for modeling and simulation. The network architecture is comprised of two neural blocks: a recurrent input layer and an output layer. The input layer is a Long-term Cognitive Network that gets unfolded in the same way as other recurrent neural networks, thus producing a sort of abstract hidden layers. In our model, we can attach meaningful linguistic labels to each neuron since the input neurons correspond to features in a given classification problem and the output neurons correspond to class labels. Moreover, we propose a variant of the backpropagation learning algorithm to compute the required parameters. This algorithm includes two new regularization components that are aimed at obtaining more interpretable knowledge representations. The numerical simulations using 58 datasets show that our model achieves higher prediction rates when compared with traditional white boxes while remaining competitive with the black boxes. Finally, we elaborate on the interpretability of our neural system using a proof of concept. [ABSTRACT FROM AUTHOR]

Memory is one of the most important mechanisms in recurrent neural networks (RNNs) learning. It plays a crucial role in practical applications, such as sequence learning. With a good memory mechanism, long term history can be fused with current information, and can thus improve RNNs learning. Developing a suitable memory mechanism is always desirable in the field of RNNs. This paper proposes a novel memory mechanism for RNNs. The main contributions of this paper are: 1) an auxiliary memory unit (AMU) is proposed, which results in a new special RNN model (AMU-RNN), separating the memory and output explicitly and 2) an efficient learning algorithm is developed by employing the technique of error flow truncation. The proposed AMU-RNN model, together with the developed learning algorithm, can learn and maintain stable memory over a long time range. This method overcomes both the learning conflict problem and gradient vanishing problem. Unlike the traditional method, which mixes the memory and output with a single neuron in a recurrent unit, the AMU provides an auxiliary memory neuron to maintain memory in particular. By separating the memory and output in a recurrent unit, the problem of learning conflicts can be eliminated easily. Moreover, by using the technique of error flow truncation, each auxiliary memory neuron ensures constant error flow during the learning process. The experiments demonstrate good performance of the proposed AMU-RNNs and the developed learning algorithm. The method exhibits quite efficient learning performance with stable convergence in the AMU-RNN learning and outperforms the state-of-the-art RNN models in sequence generation and sequence classification tasks. [ABSTRACT FROM AUTHOR]

In this paper, we consider a modified error-correction learning rule for the multilayer neural network with multivalued neurons (MLMVN). This modification is based on the soft margins technique, which leads to the minimization of the distance between a cluster center and the learning samples belonging to this cluster. MLMVN has a derivative-free learning algorithm based on the error-correction learning rule and demonstrate a higher functionality and better generalization capability than a number of other machine learning techniques. The discrete $k$ -valued multivalued neuron activation function divides a complex plane into $k$ equal sectors. For more efficient and reliable solving of classification problems it is possible to modify the MLMVN learning algorithm in such a way that learning samples belonging to different classes (clusters) will be located as close as possible to the bisector of a desired sector (the cluster center) and as far as possible from each other, respectively. Such a modification based on the soft margins learning technique is considered in this paper. This modified learning algorithm improves the generalization capability of MLMVN when solving classification problems. [ABSTRACT FROM AUTHOR]

Random Vector Functional-link (RVFL) networks, a class of learner models, can be regarded as feed-forward neural networks built with a specific randomized algorithm, i.e., the input weights and biases are randomly assigned and fixed during the training phase, and the output weights are analytically evaluated by the least square method. In this paper, we provide some insights into RVFL networks and highlight some practical issues and common pitfalls associated with RVFL-based modelling techniques. Inspired by the folklore that “all high-dimensional random vectors are almost always nearly orthogonal to each other”, we establish a theoretical result on the infeasibility of RVFL networks for universal approximation, if a RVFL network is built incrementally with random selection of the input weights and biases from a fixed scope, and constructive evaluation of its output weights. This work also addresses the significance of the scope setting of random weights and biases in respect to modelling performance. Two numerical examples are employed to illustrate our findings, which theoretically and empirically reveal some facts and limits of such class of randomized learning algorithms. [ABSTRACT FROM AUTHOR]