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...
We address the problem of autonomous race car driving. Using a recent rally game (WRC6) with realistic physics and graphics we train an Asynchronous Actor Critic (A3C) in an end-to-end fashion and propose an improved reward function to learn faster. The network is trained simultaneously on three very different tracks (snow, mountain, and coast) with various road structures, graphics and physics. Despite...
We present a reinforcement learning approach using Deep Q-Networks to steer a vehicle in a 3D physics simulation. Relying solely on camera image input the approach directly learns steering the vehicle in an end-to-end manner. The system is able to learn human driving behavior without the need of any labeled training data. An action-based reward function is proposed, which is motivated by a potential...
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,...
In the presentation major difficulties of designing neural networks are shown. It turn out that popular MLP (Multi Layer Perceptron) networks in most cases produces far from satisfactory results. Also, popular EBP (Error Back Propagation) algorithm is very slow and often is not capable to train best neural network architectures. Very powerful and fast LM (Levenberg- Marquardt) algorithm was unfortunately...
High-throughput microscopy allows fast imaging of large tissue samples, producing an unprecedented amount of sub-cellular information. The size and complexity of these data sets often out-scale current reconstruction algorithms. Overcoming this computational bottleneck requires extensive parallel processing and scalable algorithms. As high-throughput imaging techniques move into main stream research,...
Emerging general-purpose Graphics Processing Unit (GPU) provides a multi-core platform for wide applications, including machine learning algorithms. In this paper, we proposed several techniques to accelerate Support Vector Machines (SVM) on GPUs. Sparse matrix format is introduced into parallel SVM to achieve better performance. Experimental results show that the speedup of 55x-133.8x over LIBSVM...
Support Vector Machines (SVMs) are a powerful supervised learning tool, providing state-of-the-art accuracy at a cost of high computational complexity. The SVM classification suffers from linear dependencies on the number of the Support Vectors and the problem's dimensionality. In this work, we propose a scalable FPGA architecture for the acceleration of SVM classification, which exploits the device...
Task scheduling and task allocation, which are vital parts of mapping parallel programs to concurrent architectures, must take into account the interprocessor communication, whose overheads have emerged as the major performance limitation in parallel applications. Furthermore, its power consumption is an important research focus which must be addressed. Finding an optimal solution requires information...
Deep machine learning is an emerging framework for dealing with complex high-dimensionality data in a hierarchical fashion which draws some inspiration from biological sources. Despite the notable progress made in the field, there remains a need for an architecture that can represent temporal information with the same ease that spatial information is discovered. In this work, we present new results...
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...
The current commercial anti-virus software detects a virus only after the virus has appeared and caused damage. Motivated by the inference technique for detecting viruses, and a recent successful classification method, we explore a system (Radux: Reverse Analysis for Detecting Unsafe eXecutables) for automatically detecting malicious code using the collected dataset of the benign and malicious code...
Hybrid deliberative-reactive control architectures are a popular and effective approach to the control of robotic navigation applications. However, due to the fundamental differences in the design of the reactive and deliberative layers, the design of hybrid control architectures can pose significant difficulties. We propose a novel approach to improving system-level performance of hybrid control...
The high rate of data samples reported by devices that support PMU functionality forces the use of non-traditional methods in order to attempt realtime anomaly detection. Two methods discussed are offline machine learning and a realtime sliding window procedure. In using machine learning techniques it is possible to assert a classifier algorithm, which to a certain degree of accuracy can flag incoming...
Many methods for solving optimization problems, whether direct or indirect, rely upon gradient information and therefore may converge to a local optimum. Global optimization methods like Evolutionary algorithms, overcome this problem although these techniques are computationally expensive due to slow nature of the evolutionary process. In this work, a new concept is investigated to accelerate the...
The self organizing maps(SOM) has been used as a tool for mapping high-dimensional input data into a low-dimensional feature map, which has significant advantages for text clustering applications. In this paper, a novel dynamic and adaptive SOM algorithm applied to high dimensional large scale text clustering is proposed. The characteristic feature of this novel neural network model is its dynamic...
Artificial Neural Networks have previously been applied in neuro-symbolic learning to learn ground logic program rules. However, there are few results of learning relations using neuro-symbolic learning. This paper presents the system PAN, which can learn relations. The inputs to PAN are one or more atoms, representing the conditions of a logic rule, and the output is the conclusion of the rule. The...
When training a neural network it is tempting to experiment with architectures until a low total error is achieved. The danger in doing so is the creation of a network that loses generality by over-learning the training data; lower total error does not necessarily translate into a low total error in validation. The resulting network may keenly detect the samples used to train it, without being able...
Support Vector Machines is a powerful supervised learning tool. Its training phase, however, is a time-consuming task and heavily dependent on the training dataset size and dimensionality. In this work, we propose a scalable FPGA architecture for the acceleration of SVM training, which exploits the heterogeneous nature of the device and the diversities of the precision requirements among the dataset...
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.