Read by QxMD icon Read

Spaced learning

Panqu Wang, Garrison W Cottrell
What are the roles of central and peripheral vision in human scene recognition? Larson and Loschky (2009) showed that peripheral vision contributes more than central vision in obtaining maximum scene recognition accuracy. However, central vision is more efficient for scene recognition than peripheral, based on the amount of visual area needed for accurate recognition. In this study, we model and explain the results of Larson and Loschky (2009) using a neurocomputational modeling approach. We show that the advantage of peripheral vision in scene recognition, as well as the efficiency advantage for central vision, can be replicated using state-of-the-art deep neural network models...
April 1, 2017: Journal of Vision
Shinhyun Choi, Jong Hoon Shin, Jihang Lee, Patrick Sheridan, Wei D Lu
Memristors have been considered as a leading candidate for a number of critical applications ranging from non-volatile memory to non-Von Neumann computing systems. Feature extraction, which aims to transform input data from a high dimensional space to a space with fewer dimensions, is an important technique widely used in machine learning and pattern recognition applications. Here, we experimentally demonstrate that memristor arrays can be used to perform principal component analysis (PCA), one of the most commonly-used feature extraction techniques, through online, unsupervised learning...
April 24, 2017: Nano Letters
Iason Kyriazis, Evangelos Liatsikos, Odysseas Sopilidis, Panagiotis Kallidonis, Andreas Skolarikos
OBJECTIVE: Kidney puncture during percutaneous nephrolithotomy (PCNL) is regarded as one of the most demanding aspects of the procedure and only a minority of urologists perform this step without assistance by a radiologist. Currently a wide variation of fluoroscopic guided techniques is available in clinical practice. In this work we describe the most common fluoroscopic guided access techniques in a step-by-step manner aiming to assist on the standardization of their technique and terminology...
April 24, 2017: BJU International
Ya Li, Xinmei Tian, Tongliang Liu, Dacheng Tao
Multitask learning (MTL) aims to learn multiple tasks simultaneously through the interdependence between different tasks. The way to measure the relatedness between tasks is always a popular issue. There are mainly two ways to measure relatedness between tasks: common parameters sharing and common features sharing across different tasks. However, these two types of relatedness are mainly learned independently, leading to a loss of information. In this paper, we propose a new strategy to measure the relatedness that jointly learns shared parameters and shared feature representations...
April 17, 2017: IEEE Transactions on Neural Networks and Learning Systems
Long-Kai Huang, Qiang Yang, Wei-Shi Zheng
Although hash function learning algorithms have achieved great success in recent years, most existing hash models are off-line, which are not suitable for processing sequential or online data. To address this problem, this paper proposes an online hash model to accommodate data coming in stream for online learning. Specifically, a new loss function is proposed to measure the similarity loss between a pair of data samples in hamming space. Then, a structured hash model is derived and optimized in a passive-aggressive way...
April 24, 2017: IEEE Transactions on Neural Networks and Learning Systems
Junhong Lin, Ding-Xuan Zhou
Online learning algorithms in a reproducing kernel Hilbert space associated with convex loss functions are studied. We show that in terms of the expected excess generalization error, they can converge comparably fast as corresponding kernel-based batch learning algorithms. Under mild conditions on loss functions and approximation errors, fast learning rates and finite sample upper bounds are established using polynomially decreasing step-size sequences. For some commonly used loss functions for classification, such as the logistic and the p-norm hinge loss functions with p ∈ [1,2], the learning rates are the same as those for Tikhonov regularization and can be of order O(T-(1/2) log T), which are nearly optimal up to a logarithmic factor...
April 24, 2017: IEEE Transactions on Neural Networks and Learning Systems
Yuchen Guo, Guiguang Ding, Jungong Han, Yue Gao
By transferring knowledge from the abundant labeled samples of known source classes, zero-shot learning (ZSL) makes it possible to train recognition models for novel target classes that have no labeled samples. Conventional ZSL approaches usually adopt a two-step recognition strategy, in which the test sample is projected into an intermediary space in the first step, and then the recognition is carried out by considering the similarity between the sample and target classes in the intermediary space. Due to this redundant intermediate transformation, information loss is unavoidable, thus degrading the performance of overall system...
April 24, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Peihua Li, Hui Zeng, Qilong Wang, Simon Shiu, Lei Zhang
Local pooling (LP) in configuration (feature) space proposed by Boureau et al. explicitly restricts similar features to be aggregated, which can preserve as much discriminative information as possible. At the time it appeared, this method combined with sparse coding achieved competitive classification results with only a small dictionary. However, its performance lags far behind state-of-the-art results as only zero-order information is exploited. Inspired by the success of high-order statistical information in existing advanced feature coding or pooling methods, we make an attempt to address the limitation of LP...
April 19, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Bin Wang, Zhijian Ou, Zhiqiang Tan
To describe trans-dimensional observations in sample spaces of different dimensions, we propose a probabilistic model, called the trans-dimensional random field (TRF) by explicitly mixing a collection of random fields. In the framework of stochastic approximation (SA), we develop an effective training algorithm, called augmented SA, which jointly estimates the model parameters and normalizing constants while using trans-dimensional mixture sampling to generate observations of different dimensions. Furthermore, we introduce several statistical and computational techniques to improve the convergence of the training algorithm and reduce computational cost, which together enable us to successfully train TRF models on large datasets...
April 24, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
Virginie Crollen, Geneviève Albouy, Franco Lepore, Olivier Collignon
Tactile perception and motor production share the use of internally- and externally-defined coordinates. In order to examine how visual experience affects the internal/external coding of space for touch and movement, early blind (EB) and sighted controls (SC) took part in two experiments. In experiment 1, participants were required to perform a Temporal Order Judgment task (TOJ), either with their hands in parallel or crossed over the body midline. Confirming previous demonstration, crossing the hands led to a significant decrement in performance in SC but did not affect EB...
April 21, 2017: Scientific Reports
Martin A San, L Rela, B D Gelb, M R Pagani
In contrast to trials of training without intervals (massed training), training trials spaced over time (spaced training) induce a more persistent memory identified as long-term memory (LTM). This phenomenon known as "the spacing effect for memory" is poorly understood. LTM is supported by structural synaptic plasticity; however, how synapses integrate spaced stimuli remains elusive. Here, we analyzed events of structural synaptic plasticity at the single synapse level after distinct patterns of stimulation in motoneurons of Drosophila We found that the spacing effect is a phenomenon detected at synaptic level, which determine the specificity and the precision in structural synaptic plasticity...
April 21, 2017: Journal of Neuroscience: the Official Journal of the Society for Neuroscience
Rhys Heffernan, Yuedong Yang, Kuldip Paliwal, Yaoqi Zhou
Motivation: The accuracy of predicting protein local and global structural properties such as secondary structure and solvent accessible surface area has been stagnant for many years because of the challenge of accounting for non-local interactions between amino acid residues that are close in three-dimensional structural space but far from each other in their sequence positions. All existing machine-learning techniques relied on a sliding window of 10-20 amino acid residues to capture some "short to intermediate" non-local interactions...
April 18, 2017: Bioinformatics
Timothy Doster, Abbie T Watnik
Orbital angular momentum (OAM) beams allow for increased channel capacity in free-space optical communication. Conventionally, these OAM beams are multiplexed together at a transmitter and then propagated through the atmosphere to a receiver where, due to their orthogonality properties, they are demultiplexed. We propose a technique to demultiplex these OAM-carrying beams by capturing an image of the unique multiplexing intensity pattern and training a convolutional neural network (CNN) as a classifier. This CNN-based demultiplexing method allows for simplicity of operation as alignment is unnecessary, orthogonality constraints are loosened, and costly optical hardware is not required...
April 20, 2017: Applied Optics
Dante A Pertusi, Gregory O'Donnell, Michelle F Homsher, Kelli Solly, Amita Patel, Shannon L Stahler, Daniel Riley, Michael F Finley, Eleftheria N Finger, Gregory C Adam, Juncai Meng, David J Bell, Paul D Zuck, Edward M Hudak, Michael J Weber, Jennifer E Nothstein, Louis Locco, Carissa Quinn, Adam Amoss, Brian Squadroni, Michelle Hartnett, Mee Ra Heo, Tara White, S Alex May, Evelyn Boots, Kenneth Roberts, Patrick Cocchiarella, Alex Wolicki, Anthony Kreamer, Peter S Kutchukian, Anne Mai Wassermann, Victor N Uebele, Meir Glick, Andrew Rusinko, J Christopher Culberson
High-throughput screening (HTS) is a widespread method in early drug discovery for identifying promising chemical matter that modulates a target or phenotype of interest. Because HTS campaigns involve screening millions of compounds, it is often desirable to initiate screening with a subset of the full collection. Subsequently, virtual screening methods prioritize likely active compounds in the remaining collection in an iterative process. With this approach, orthogonal virtual screening methods are often applied, necessitating the prioritization of hits from different approaches...
April 1, 2017: SLAS Discovery
Satoshi Eifuku
First, Brodmann areas 27, 28, 36 and 37, were anatomically defined in the beginning of this review. These areas exist in the parahippocampal or fusiform gyrus of the ventral temporal lobe in humans. Subsequently, the current understanding of their functions was summarized on the basis of recent findings mainly through human functional neuroimaging studies and animal studies. Rodent studies have shown the existence of neuronal activities for representing space, such as those involving head-direction cells or grid cells, in areas 27 (the parasubicular cortex) and 28 (the ventral entorhinal cortex)...
April 2017: Brain and Nerve, Shinkei Kenkyū No Shinpo
Hongwei Hu, Bo Ma, Jianbing Shen, Ling Shao
In this paper, we propose a manifold regularized correlation tracking method with augmented samples. To make better use of the unlabeled data and the manifold structure of the sample space, a manifold regularization-based correlation filter is introduced, which aims to assign similar labels to neighbor samples. Meanwhile, the regression model is learned by exploiting the block-circulant structure of matrices resulting from the augmented translated samples over multiple base samples cropped from both target and nontarget regions...
April 12, 2017: IEEE Transactions on Neural Networks and Learning Systems
Xuelong Li, Lina Liu, Xiaoqiang Lu
Person reidentification usually refers to matching people in different camera views in nonoverlapping multicamera networks. Many existing methods learn a similarity measure by projecting the raw feature to a latent subspace to make the same target's distance smaller than different targets' distances. However, the same targets captured in different camera views should hold the same intrinsic attributes while different targets should hold different intrinsic attributes. Projecting all the data to the same subspace would cause loss of such an information and comparably poor discriminability...
April 12, 2017: IEEE Transactions on Neural Networks and Learning Systems
Jun Lu, Zhongtao Yang, Klaus Okkelberg, Maysam Ghovanloo
BACKGROUND: Tongue tracking, which helps researchers gain valuable insights into speech mechanism, has many applications in speech therapy and language learning. The wireless localization technique, which involves tracking a small magnetic tracer within the 3-D oral space, provides a low cost and convenient approach to capture tongue kinematics. In practice, this technique requires accurate calibration of 3-axial magnetic sensors used in the tracking system. The data-driven calibration depends on the trajectories of magnetic tracer and the ambient noise, which may change across time and space...
April 12, 2017: IEEE Transactions on Bio-medical Engineering
Nicolás Navarro-Guerrero, Robert J Lowe, Stefan Wermter
Both nociception and punishment signals have been used in robotics. However, the potential for using these negatively valenced types of reinforcement learning signals for robot learning has not been exploited in detail yet. Nociceptive signals are primarily used as triggers of preprogrammed action sequences. Punishment signals are typically disembodied, i.e., with no or little relation to the agent-intrinsic limitations, and they are often used to impose behavioral constraints. Here, we provide an alternative approach for nociceptive signals as drivers of learning rather than simple triggers of preprogrammed behavior...
2017: Frontiers in Neurorobotics
Yuhang Zhang, Saurabh Prasad, Atilla Kilicarslan, Jose L Contreras-Vidal
With the development of Brain Machine Interface (BMI) systems, people with motor disabilities are able to control external devices to help them restore movement abilities. Longitudinal validation of these systems is critical not only to assess long-term performance reliability but also to investigate adaptations in electrocortical patterns due to learning to use the BMI system. In this paper, we decode the patterns of user's intended gait states (e.g., stop, walk, turn left, and turn right) from scalp electroencephalography (EEG) signals and simultaneously learn the relative importance of different brain areas by using the multiple kernel learning (MKL) algorithm...
2017: Frontiers in Neuroscience
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"