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.
Training of artificial neural networks (ANNs) using reinforcement learning (RL) techniques is being widely discussed in the robot learning literature. The high model complexity of ANNs along with the model-free nature of RL algorithms provides a desirable combination for many robotics applications. There is a huge need for algorithms that generalize using raw sensory inputs, such as vision, without...
Traffic sign recognition is an important step for integrating smart vehicles into existing road transportation systems. In this paper, an NVIDIA Jetson TX1-based traffic sign recognition system is introduced for driver assistance applications. The system incorporates two major operations, traffic sign detection and recognition. Image color and shape based detection is used to locate potential signs...
In game artificial intelligence (AI), two common directions for developing non-human computer players are strong AI and human-like AI. Human-like AI aims at making computer agents behave like humans. In this direction, NeuroEvolution (NE), which is a combination of an artificial neural network (ANN) and an evolutionary algorithm (EA), had been frequently used to a make computer agent to behave like...
In a game it is often the case that there are multiple roles or types of actors with different goals. One possible target for automatic content generation is to create multiple different software agents for these distinct roles. This paper outlines a technique, based on the multiple worlds model, for creating such actors via evolution. The objective function is based on the performance of the actors...
The Open University of Israel offers a program of study for Computer Science graduates towards a high school Teaching Certificate in Computer Science. The program is unique in that it enables studying towards the certificate in a distance learning environment and therefore can be pursued by people who wish to combine further education with careers and personal responsibilities. In this paper we describe...
We consider learning a distance metric in a weakly supervised setting where bags (or sets) of instances are labeled with bags of labels. A general approach is to formulate the problem as a Multiple Instance Learning (MIL) problem where the metric is learned so that the distances between instances inferred to be similar are smaller than the distances between instances inferred to be dissimilar. Classic...
The relationship between the use of Geogebra and Technological Pedagogical Content and Knowledge (TPACK) by teachers has not been fully investigated and understood. Therefore, the aim of this study was to integrate GeoGebra technology to develop the TPACK of secondary school pre-service mathematics teachers. The participants of this study were 60 Indian teachers. Data were collected through the administration...
Identify the serious games that best meet the needs and expectations of teachers and pedagogical objectives of their courses remains a necessity about the integration of serious games in the learning process. Indeed, several serious games have developed in recent years, and it is often difficult for a teacher, not a computer scientist in particular, to find and choose a game that meets its specific...
Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in...
This paper describes a Learning Design (LD) tool, aimed at supporting teachers' conceptualization of collaborative learning activities for students. The main element of innovation of the tool, called the "augmented 4Ts game", in respect to the other existing LD tools, lays in its being half-tangible-half-digital. The tangible component of the game is based on a paper board and a set of cards,...
While there is a large amount of text data on the Internet, people need to organize the text data with experienced category. However, the flat structure of categories could not satisfy the modern information management. To solve this problem, we propose a hierarchical classification process with a strategy, called candidates, used to relieve the blocking problems. Besides, we establish the description...
We investigate the problem of representing an entire video using CNN features for human action recognition. End-to-end learning of CNN/RNNs is currently not possible for whole videos due to GPU memory limitations and so a common practice is to use sampled frames as inputs along with the video labels as supervision. However, the global video labels might not be suitable for all of the temporally local...
A key challenge of facial expression recognition (FER) is to develop effective representations to balance the complex distribution of intra- and inter- class variations. The latest deep convolutional networks proposed for FER are trained by penalizing the misclassification of images via the softmax loss. In this paper, we show that better FER performance can be achieved by combining the deep metric...
We investigate different strategies for active learning with Bayesian deep neural networks. We focus our analysis on scenarios where new, unlabeled data is obtained episodically, such as commonly encountered in mobile robotics applications. An evaluation of different strategies for acquisition, updating, and final training on the CIFAR-10 dataset shows that incremental network updates with final training...
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space...
We propose a self-supervised approach for learning representations of relationships between humans and their environment, including object interactions, attributes, and body pose, entirely from unlabeled videos recorded from multiple viewpoints (Fig. 2). We train an embedding with a triplet loss that contrasts a pair of simultaneous frames from different viewpoints with temporally adjacent and visually...
This paper introduces an end-to-end fine-tuning method to improve hand-eye coordination in modular deep visuomotor policies (modular networks) where each module is trained independently. Benefiting from weighted losses, the fine-tuning method significantly improves the performance of the policies for a robotic planar reaching task.
Stationarity of reconstruction problems is the crux to enabling convolutional neural networks for many image processing tasks: the output estimate for a pixel is generally not dependent on its location within the image but only on its immediate neighbourhood. We expect other invariances, too. For most pixel-processing tasks, rigid transformations should commute with the processing: a rigid transformation...
In this paper, we focus on constructing an accurate super resolution system based on multiple Convolution Neural Networks (CNNs). Each individual CNN is trained separately with different network structure. A Context-wise Network Fusion (CNF) approach is proposed to integrate the outputs of individual networks by additional convolution layers. With fine-tuning the whole fused network, the accuracy...
In this paper, balanced two-stage residual networks (BTSRN) are proposed for single image super-resolution. The deep residual design with constrained depth achieves the optimal balance between the accuracy and the speed for super-resolving images. The experiments show that the balanced two-stage structure, together with our lightweight two-layer PConv residual block design, achieves very promising...
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.