The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this work a novel approach to Transfer Learning for the use in Deep Reinforcement Learning is introduced. The agent is realized as an actor-critic framework, namely the Deep Deterministic Policy Gradient algorithm. The Q-function and the policy are represented as deep feed-forward networks, that are trained by minimizing the mean squared Bellman error and by maximizing the expected reward, respectively...
Neural networks are a powerful function approximation tool which has the ability to model any function with arbitrary precision. For any function as a black box, it is able to reconstruct the function given the target and the input data. However, there are problems where the target is at least partially unknown. In such cases it is impossible for a traditional neural network to compute the gradient...
Deep Q-Learning is an effective reinforcement learning method, which has recently obtained human-level performance for a set of Atari 2600 games. Remarkably, the system was trained on the high-dimensional raw visual data. Is Deep Q-Learning equally valid for problems involving a low-dimensional state space? To answer this question, we evaluate the components of Deep Q-Learning (deep architecture,...
Though several approaches have already been proposed in the literature to evolve neural network topologies for solving a wide range of machine learning tasks, this paper presents an alternative one, capable of evolving arbitrarily connected feed forward neural networks (ACFNNs), including linear and nonlinear neurons. A genetic algorithm is conceived to adjust the topology and also to perform variable...
Aiming at difficulty modeling of large amounts of industrial process data, a novel soft sensor model based on artificial immune agent-based multiple model Radial Basis Function (RBF) networks is proposed in this paper. The method is to predict the qualities of manufactured products of Crude Oil Tower. In the IMMST-Team system, some biological immune based operation and learning rules which can efficiently...
This paper describes the possibilities of using artificial neural networks in the following fields of machine learning: data mining and semantic integration in large databases. Possibility of using analog components for developing neural networks is investigated.
Particle swarm optimization (PSO), a new promising evolutionary optimization technique, has a wide range of application in optimization problems including training of artificial neural networks. In this paper, an attempt is made to completely train a RBF neural network architecture including the centers, optimum spreads, and the number of hidden units. The proposed method has been evaluated on some...
An application of TNN on the damage detection of steel bridge structures is presented. The issues relating to the design of network and learning algorithm are addressed and network architectures have been developed with reference to trussed bridge structures. The training patterns are generated for multiple damaged zones in a structure. The results of simulation show that the algorithm is suitable...
Designing less intrusive intelligent environments requires a deep understanding of activities that a user is engaged in. This paper presents a novel one-pass neural network system that uses unobtrusive and relatively simple sensors and puts forward a constructive algorithm which is able to recognize different high level activities (such as ldquosleepingrdquo, ldquowashingrdquo, ldquoworking at computerrdquo)...
A system of neural networks in a multistage architecture is proposed to resolve the components of a transient signal. The motivation of the design was a desire to use smaller networks that compute a binary decision allowing the use of the multilayer perceptron design algorithm for faster and more effective training, and to cascade these simple networks into a pipeline architecture for efficient implementation...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.