OALib Journal期刊

ISSN: 2333-9721



匹配条件: “Haris MEMISEVIC” ,找到相关结果约234条。
Journal of Special Education and Rehabilitation , 2013, DOI: 10.2478/v10215-011-0032-4
Abstract: Fine motor skills are prerequisite for many everyday activities and they are a good predictor of a child's later academic outcome. The goal of the present study was to assess the effects of age on the development of fine motor coordination and visual-motor integration in preschool children. The sample for this study consisted of 276 preschool children from Canton Sara-jevo, Bosnia and Herzegovina. We assessed children's motor skills with Beery Visual Motor Integration Test and Lafayette Pegboard Test. Data were analyzed with one-way ANOVA, followed by planned com-parisons between the age groups. We also performed a regression analysis to assess the influence of age and motor coordination on visual-motor integration. The results showed that age has a great effect on the development of fine motor skills. Furthermore, the results indicated that there are possible sensitive periods at preschool age in which the development of fine motor skills is accelerated. Early intervention specialists should make a thorough evaluations of fine motor skills in preschool children and make motor (re)habilitation programs for children at risk of fine motor delays.
Journal of Special Education and Rehabilitation , 2010,
Abstract: The goal of the present study was to examine the effects of short-term equine-assisted therapy as a complementary therapy modality for children with autism spectrum disorders (ASD). There were four children in the study, two boys and two girls from ages 8 to 10 years, with ASD included in this study. All of the children were attending a special education school in Sarajevo, Bosnia and Herzegovina. The equine-assisted therapy sessions took place once a week for a period of 10 weeks. The results of the study revealed positive effects the therapy had in two of the four children as measured by the Autism Treatment Evaluation Checklists (ATEC). The improvement was reported in the domains of speech, socialization, sensory/ cognitive awareness and health/behavior. The authors propose a more widely use of this therapeutic modality in the psychoeducational treatment of children with ASD.
Secure Tropos: An Agent Oriented Software Engineering Methodology for the Development of Health and Social Care Information Systems
International Journal of Computer Science and Security , 2009,
Abstract: A huge amount of health and social care related information needs to be stored and analysed; with the aid of computer systems this can be done faster and more efficiently. As a result, computerised health and social care information systems are gaining popularity. The development of such systems, mostly so far, follows an ad-hoc pattern. However, in order to effectively deal with the characteristics of such systems such as size, security, unpredictability, and openness; appropriate software engineering methodologies and paradigms should be employed for their development. This paper defines a set of requirements that a methodology should demonstrate and it argues for the appropriateness of the Secure Tropos agent oriented methodology for the development of health and social care information systems. The applicability of the methodology is demonstrated with the aid of a real-life case study, the electronic Single Assessment Process system, an information system to support integrated assessment of the health and social care needs of older people. The application of the proposed methodology on the case study indicated that the methodology satisfies the identified requirements.
Learning to relate images: Mapping units, complex cells and simultaneous eigenspaces
Roland Memisevic
Physics , 2011,
Abstract: A fundamental operation in many vision tasks, including motion understanding, stereopsis, visual odometry, or invariant recognition, is establishing correspondences between images or between images and data from other modalities. We present an analysis of the role that multiplicative interactions play in learning such correspondences, and we show how learning and inferring relationships between images can be viewed as detecting rotations in the eigenspaces shared among a set of orthogonal matrices. We review a variety of recent multiplicative sparse coding methods in light of this observation. We also review how the squaring operation performed by energy models and by models of complex cells can be thought of as a way to implement multiplicative interactions. This suggests that the main utility of including complex cells in computational models of vision may be that they can encode relations not invariances.
On multi-view feature learning
Roland Memisevic
Computer Science , 2012,
Abstract: Sparse coding is a common approach to learning local features for object recognition. Recently, there has been an increasing interest in learning features from spatio-temporal, binocular, or other multi-observation data, where the goal is to encode the relationship between images rather than the content of a single image. We provide an analysis of multi-view feature learning, which shows that hidden variables encode transformations by detecting rotation angles in the eigenspaces shared among multiple image warps. Our analysis helps explain recent experimental results showing that transformation-specific features emerge when training complex cell models on videos. Our analysis also shows that transformation-invariant features can emerge as a by-product of learning representations of transformations.
Unsupervised learning of depth and motion
Kishore Konda,Roland Memisevic
Computer Science , 2013,
Abstract: We present a model for the joint estimation of disparity and motion. The model is based on learning about the interrelations between images from multiple cameras, multiple frames in a video, or the combination of both. We show that learning depth and motion cues, as well as their combinations, from data is possible within a single type of architecture and a single type of learning algorithm, by using biologically inspired "complex cell" like units, which encode correlations between the pixels across image pairs. Our experimental results show that the learning of depth and motion makes it possible to achieve state-of-the-art performance in 3-D activity analysis, and to outperform existing hand-engineered 3-D motion features by a very large margin.
Regularizing RNNs by Stabilizing Activations
David Krueger,Roland Memisevic
Computer Science , 2015,
Abstract: We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regularizer for RNNs including LSTMs and IRNNs, improving performance on character-level language modelling and phoneme recognition, and outperforming weight noise and dropout. We set state of the art (17.5% PER) for an RNN on the TIMIT phoneme recognition task, without using beam-search. With this penalty term, IRNN can achieve similar performance to LSTM on language modelling, although adding the penalty term to the LSTM results in superior performance. Our penalty term also prevents the exponential growth of IRNN's activations outside of their training horizon, allowing them to generalize to much longer sequences.
Feature grouping from spatially constrained multiplicative interaction
Felix Bauer,Roland Memisevic
Computer Science , 2013,
Abstract: We present a feature learning model that learns to encode relationships between images. The model is defined as a Gated Boltzmann Machine, which is constrained such that hidden units that are nearby in space can gate each other's connections. We show how frequency/orientation "columns" as well as topographic filter maps follow naturally from training the model on image pairs. The model also helps explain why square-pooling models yield feature groups with similar grouping properties. Experimental results on synthetic image transformations show that spatially constrained gating is an effective way to reduce the number of parameters and thereby to regularize a transformation-learning model.
Four new Tenthredo Linnaeus, 1758 species from Sikkim (Hymenoptera, Tenthredinidae)
Haris, Attila
Graellsia , 2004,
Abstract: Four new Tenthredo Linnaeus, 1758 species are described from Sikkim, India: T. nigroypsilon sp. n. , T. memoriaescalerai sp. n., T. allantosikkimensis sp. n. and Tenthredo minutosimplicis sp. n. and compared to T. maruana Malaise, 1945, T. variicolor Malaise, 1945, T. maculipennis Malaise, 1945, T. coloripleuris Malaise, 1945 and T. changbuensis Haris, 2000. Se describen cuatro nuevas especies de Tenthredo Linnaeus, 1758 procedentes de Sikkim, India: T. nigroypsilon sp. n., T. memoriaescalerai sp. n., T. allantosikkimensis sp. n. y Tenthredo minutosimplicis sp. n. y se comparan con T. maruana Malaise, 1945, T. variicolor Malaise, 1945, T. maculipennis Malaise, 1945, T. coloripleuris Malaise, 1945 y T. changbuensis Haris, 2000.
New sawflies from Spain (Hymenoptera, Tenthredinidae)
Haris, Attila
Graellsia , 2004,
Abstract: Dolerus varispinus Hartig, 1837; Nematus respondens F rster, 1854; Pristiphora kamtchatica Malaise, 1931 and Pristiphora nievesi sp. n. are recorded from Spain for the first time. The description of Pristiphora nievesi sp. n. is given and compared to P. subbifida (Thomson, 1871); P. carpentieri Konow, 1903 and P. parnasia Konow, 1902. Las especies Dolerus varispinus Hartig, 1837; Nematus respondens F rster, 1854 y Pristiphora kamtchatica Malaise, 1931 se citan por primera vez en Espa a. Se describe Pristiphora nievesi sp. n. y se compara con P. subbifida (Thomson, 1871); P. carpentieri Konow, 1903 y P. parnasia Konow, 1902.

Copyright © 2008-2017 Open Access Library. All rights reserved.