Read by QxMD icon Read

Problem base learning

Chunjie Zhang, Jian Cheng, Qi Tian
Visual features have been widely used for image representation and categorization. However, visual features are often inconsistent with human perception. Besides, constructing explicit semantic space is still an open problem. To alleviate these two problems, in this paper, we propose to construct structured weak semantic space for image representation. Exemplar classifier is first trained to separate each training image from other images for weak semantic space construction. However, each exemplar classifier separates one training image from other images, and it only has limited semantic separability...
August 11, 2017: IEEE Transactions on Neural Networks and Learning Systems
Daniil Kononenko, Yaroslav Ganin, Diana Sungatullina, Victor Lempitsky
We propose a general approach to the gaze redirection problem in images that utilizes machine learning. The idea is to learn to re-synthesize images by training on pairs of images with known disparities between gaze directions. We show that such learning-based re-synthesis can achieve convincing gaze redirection based on monocular input, and that the learned systems generalize well to people and imaging conditions unseen during training.
August 14, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
A N Gorban, I Y Tyukin
The problem of non-iterative one-shot and non-destructive correction of unavoidable mistakes arises in all Artificial Intelligence applications in the real world. Its solution requires robust separation of samples with errors from samples where the system works properly. We demonstrate that in (moderately) high dimension this separation could be achieved with probability close to one by linear discriminants. Based on fundamental properties of measure concentration, we show that for M<aexp(bn) random M-element sets in R(n) are linearly separable with probability p, p>1-ϑ, where 1>ϑ>0 is a given small constant...
July 31, 2017: Neural Networks: the Official Journal of the International Neural Network Society
MohammadMehdi Kafashan, ShiNung Ching
A long-standing and influential hypothesis in neural information processing is that early sensory networks adapt themselves to produce efficient codes of afferent inputs. Here, we show how a nonlinear recurrent network provides an optimal solution for the efficient coding of an afferent input and its history. We specifically consider the problem of producing lightweight codes, ones that minimize both ℓ1 and ℓ2 constraints on sparsity and energy, respectively. When embedded in a linear coding paradigm, this problem results in a non-smooth convex optimization problem...
July 22, 2017: Neural Networks: the Official Journal of the International Neural Network Society
Elisa Maes, Elias Vanderoost, Rudi D'Hooge, Jan De Houwer, Tom Beckers
In an associative patterning task, some people seem to focus more on learning an overarching rule, whereas others seem to focus on acquiring specific relations between the stimuli and outcomes involved. Building on earlier work, we further investigated which cognitive factors are involved in feature- vs. rule-based learning and generalization. To this end, we measured participants' tendency to generalize according to the rule of opposites after training on negative and positive patterning problems (i.e., A+/B+/AB- and C-/D-/CD+), their tendency to attend to global aspects or local details of stimuli, their systemizing disposition and their score on the Raven intelligence test...
2017: Frontiers in Psychology
Martin Gjoreski, Mitja Luštrek, Matjaž Gams, Hristijan Gjoreski
Being able to detect stress as it occurs can greatly contribute to dealing with its negative health and economic consequences. However, detecting stress in real life with an unobtrusive wrist device is a challenging task. The objective of this study is to develop a method for stress detection that can accurately, continuously and unobtrusively monitor psychological stress in real life. First, we explore the problem of stress detection using machine learning and signal processing techniques in laboratory conditions, and then we apply the extracted laboratory knowledge to real-life data...
August 10, 2017: Journal of Biomedical Informatics
Vivian Puplampu
There is evidence supporting student-centered learning (SCL) as an effective pedagogy to prepare professionals to work in the evolving health care system of the twenty-first century. SCL has many benefits, among them that it helps students to learn to work in teams and develop problem-solving, critical thinking and communication skills. The focus on the student means that the teacher's power is decreased. This, along with openness of the approach, can make the transition to SCL a challenge. This study used an exploratory descriptive qualitative design to explore how comfortable nursing students and faculty members were in a context-based learning (CBL) program, a version of SCL...
July 28, 2017: International Journal of Nursing Education Scholarship
F Dornaika, R Dahbi, A Bosaghzadeh, Y Ruichek
Most of graph construction techniques assume a transductive setting in which the whole data collection is available at construction time. Addressing graph construction for inductive setting, in which data are coming sequentially, has received much less attention. For inductive settings, constructing the graph from scratch can be very time consuming. This paper introduces a generic framework that is able to make any graph construction method incremental. This framework yields an efficient and dynamic graph construction method that adds new samples (labeled or unlabeled) to a previously constructed graph...
July 24, 2017: Neural Networks: the Official Journal of the International Neural Network Society
Warunee Fongkaew, Warawan Udomkhamsuk, Nongkran Viseskul, Marisa Guptaruk
Youth living with HIV face difficult and challenging situations that decrease their adherence to antiretroviral medications. In this study, we developed a pilot program to enhance HIV treatment adherence and risk reduction among youth living with HIV based on collaboration with a community hospital involving a multi-disciplinary healthcare team. Participants were 25 youth living with HIV/AIDS, 18 caregivers, and 12 healthcare providers. The action research process comprised a preliminary stage and four phases of assessment, planning, implementation, and evaluation...
August 11, 2017: Nursing & Health Sciences
Sandra Johnston, Fiona Coyer, Robyn Nash
Upon completion of undergraduate nursing courses, new graduates are expected to transition seamlessly into practice. Education providers face challenges in the preparation of undergraduate nurses due to increasing student numbers and decreasing availability of clinical placement sites. High fidelity patient simulation is an integral component of nursing curricula as an adjunct to preparation for clinical placement. Debriefing after simulation is an area where the underlying structure of problems can consciously be explored...
August 3, 2017: Nurse Education in Practice
Sofia Savvaki, Grigorios Tsagkatakis, Athanasia Panousopoulou, Panagiotis Tsakalides
Sensor-based activity recognition is encountered in innumerable applications of the arena of pervasive healthcare and plays a crucial role in biomedical research. Nonetheless, the frequent situation of unobserved measurements impairs the ability of machine learning algorithms to efficiently extract context from raw streams of data. In this work, we study the problem of accurate estimation of missing multi-modal inertial data and we propose a classification framework that considers the reconstruction of sub-sampled data during the test phase...
August 7, 2017: IEEE Journal of Biomedical and Health Informatics
Mingliang Xu, Jiejie Zhu, Pei Lv, Bing Zhou, Marshall F Tappen, Rongrong Ji
This paper addresses the problem of recognizing and removing shadows from monochromatic natural images from a learning based perspective. Without chromatic information, shadow recognition and removal are extremely challenging in the literature, mainly due to the missing of invariant color cues. Natural scenes make this problem even harder due to the complex illumination condition and ambiguity from many near-black objects. In this paper, a learning based shadow recognition and removal scheme is proposed to tackle the challenges above...
August 7, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Zhenyong Fu, Tao Xiang, Elyor Kodirov, Shaogang Gong
Zero-Shot Learning (ZSL) for visual recognition is typically achieved by exploiting a semantic embedding space. In such a space, both seen and unseen class labels as well as image features can be embedded so that the similarity among them can be measured directly. In this work, we consider that the key to effective ZSL is to compute an optimal distance metric in the semantic embedding space. Existing ZSL works employ either Euclidean or cosine distances. However, in a high-dimensional space where the projected class labels (prototypes) are sparse, these distances are suboptimal, resulting in a number of problems including hubness and domain shift...
August 7, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
Betul Erdogdu Sakar, Gorkem Serbes, C Okan Sakar
The recently proposed Parkinson's Disease (PD) telediagnosis systems based on detecting dysphonia achieve very high classification rates in discriminating healthy subjects from PD patients. However, in these studies the data used to construct the classification model contain the speech recordings of both early and late PD patients with different severities of speech impairments resulting in unrealistic results. In a more realistic scenario, an early telediagnosis system is expected to be used in suspicious cases by healthy subjects or early PD patients with mild speech impairment...
2017: PloS One
Fuzhen Zhuang, Xuebing Li, Xin Jin, Dapeng Zhang, Lirong Qiu, Qing He
Multitask learning (MTL) aims to learn multiple related tasks simultaneously instead of separately to improve the generalization performance of each task. Most existing MTL methods assumed that the multiple tasks to be learned have the same feature representation. However, this assumption may not hold for many real-world applications. In this paper, we study the problem of MTL with heterogeneous features for each task. To address this problem, we first construct an integrated graph of a set of bipartite graphs to build a connection among different tasks...
August 3, 2017: IEEE Transactions on Cybernetics
Hong Jia, Yiu-Ming Cheung
In clustering analysis, data attributes may have different contributions to the detection of various clusters. To solve this problem, the subspace clustering technique has been developed, which aims at grouping the data objects into clusters based on the subsets of attributes rather than the entire data space. However, the most existing subspace clustering methods are only applicable to either numerical or categorical data, but not both. This paper, therefore, studies the soft subspace clustering of data with both of the numerical and categorical attributes (also simply called mixed data for short)...
August 3, 2017: IEEE Transactions on Neural Networks and Learning Systems
Yuping Wang, Haiyan Liu, Fei Wei, Tingting Zong, Xiaodong Li
For a large-scale global optimization (LSGO) problem, divide-and-conquer is usually considered as an effective strategy to decompose the problem into smaller subproblems, each of which can be then solved individually. Among these decomposition methods, variable grouping is shown to be promising in recent years. Existing variable grouping methods usually assume the problem to be black-box (i.e., assuming that an analytical model of the objective function is unknown), and they attempt to learn appropriate variable grouping that would allow for a better decomposition of the problem...
August 9, 2017: Evolutionary Computation
Rongrong Ji, Hong Liu, Liujuan Cao, Di Liu, Yongjian Wu, Feiyue Huang
Binary code learning, a.k.a. hashing, has received increasing attention in large-scale visual search. By transforming high-dimensional features to binary codes, the original Euclidean distance is approximated via Hamming distance. More recently, it is advocated that it is the manifold distance, rather than the Euclidean distance, that should be preserved in the Hamming space. However, it retains as an open problem to directly preserve the manifold structure by hashing. In particular, it needs first to build the local linear embedding in the original feature space, and then quantize such embedding to binary codes...
August 2, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Diana P S R P Carvalho, Isabelle C Azevedo, Giovanna K P Cruz, Gabriela A C Mafra, Anna L C Rego, Allyne F Vitor, Viviane E P Santos, Ana L P Cogo, Marcos A Ferreira Júnior
OBJECTIVE: Identifying the strategies used to promote critical thinking (CT) during undergraduate education in nursing courses. DESIGN: Systematic review. SOURCE OF DATA: Five electronic databases were searched without language, publication time or geographic filters. METHOD: A systematic review of the literature. Including experimental studies that considered at least one teaching strategy to promote critical thinking of undergraduate students in Nursing courses...
July 29, 2017: Nurse Education Today
Yusen Zhan, Haitham Bou Ammar, Matthew E Taylor
Policy search is a class of reinforcement learning algorithms for finding optimal policies in control problems with limited feedback. These methods have been shown to be successful in high-dimensional problems such as robotics control. Though successful, current methods can lead to unsafe policy parameters that potentially could damage hardware units. Motivated by such constraints, we propose projection-based methods for safe policies. These methods, however, can handle only convex policy constraints. In this letter, we propose the first safe policy search reinforcement learner capable of operating under nonconvex policy constraints...
August 4, 2017: Neural Computation
Fetch more papers »
Fetching more papers... Fetching...
Read by QxMD. Sign in or create an account to discover new knowledge that matter to you.
Remove bar
Read by QxMD icon Read

Search Tips

Use Boolean operators: AND/OR

diabetic AND foot
diabetes OR diabetic

Exclude a word using the 'minus' sign

Virchow -triad

Use Parentheses

water AND (cup OR glass)

Add an asterisk (*) at end of a word to include word stems

Neuro* will search for Neurology, Neuroscientist, Neurological, and so on

Use quotes to search for an exact phrase

"primary prevention of cancer"
(heart or cardiac or cardio*) AND arrest -"American Heart Association"