Read by QxMD icon Read

representational learning

Cristian Axenie, Christoph Richter, Jörg Conradt
Biological and technical systems operate in a rich multimodal environment. Due to the diversity of incoming sensory streams a system perceives and the variety of motor capabilities a system exhibits there is no single representation and no singular unambiguous interpretation of such a complex scene. In this work we propose a novel sensory processing architecture, inspired by the distributed macro-architecture of the mammalian cortex. The underlying computation is performed by a network of computational maps, each representing a different sensory quantity...
October 20, 2016: Sensors
Huaping Liu, Jie Qin, Fuchun Sun, Di Guo
Tactile sensors play very important role for robot perception in the dynamic or unknown environment. However, the tactile object recognition exhibits great challenges in practical scenarios. In this paper, we address this problem by developing an extreme kernel sparse learning methodology. This method combines the advantages of extreme learning machine and kernel sparse learning by simultaneously addressing the dictionary learning and the classifier design problems. Furthermore, to tackle the intrinsic difficulties which are introduced by the representer theorem, we develop a reduced kernel dictionary learning method by introducing row-sparsity constraint...
October 19, 2016: IEEE Transactions on Cybernetics
Li Liu, Zijia Lin, Ling Shao, Fumin Shen, Guiguang Ding, Jungong Han
With the dramatic development of the Internet, how to exploit large-scale retrieval techniques for multimodal web data has become one of the most popular but challenging problems in computer vision and multimedia. Recently, hashing methods are used for fast nearest neighbor search in large-scale data spaces, by embedding high-dimensional feature descriptors into a similarity-preserving Hamming space with a low dimension. Inspired by this, in this paper, we introduce a novel supervised cross-modality hashing framework which can generate unified binary codes for instances represented in different modalities...
October 19, 2016: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Yang Cong, Ji Liu, Gan Sun, Quanzeng You, Yuncheng Li, Jiebo Luo
Initializing an effective dictionary is an indispensable step for sparse representation. In this paper, we focus on the dictionary selection problem with the objective to select a compact subset of basis from original training data instead of learning a new dictionary matrix as dictionary learning models do. We first design a new dictionary selection model via `2;0 norm. For model optimization, we propose two methods: one is the standard forward-backward greedy algorithm, which is not suitable for large-scale problems; the other is based on the gradient cues at each forward iteration and speeds up the process dramatically...
October 19, 2016: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Pierre-Henri Conze, Vincent Noblet, François Rousseau, Fabrice Heitz, Vito de Blasi, Riccardo Memeo, Patrick Pessaux
PURPOSE: Toward an efficient clinical management of hepatocellular carcinoma (HCC), we propose a classification framework dedicated to tumor necrosis rate estimation from dynamic contrast-enhanced CT scans. Based on machine learning, it requires weak interaction efforts to segment healthy, active and necrotic liver tissues. METHODS: Our contributions are two-fold. First, we apply random forest (RF) on supervoxels using multi-phase supervoxel-based features that discriminate tissues based on their dynamic in response to contrast agent injection...
October 22, 2016: International Journal of Computer Assisted Radiology and Surgery
Yi-Shin Sheu, Susan M Courtney
Conflict between multiple sensory stimuli or potential motor responses is thought to be resolved via bias signals from prefrontal cortex (PFC). However, population codes in the PFC also represent abstract information, such as task rules. How is conflict between active abstract representations resolved? We used functional neuroimaging to investigate the mechanism responsible for resolving conflict between abstract representations of task rules. Participants performed two different tasks based on a cue. We manipulated the degree of conflict at the task-rule level by training participants to associate the color and shape dimensions of the cue with either the same task rule (congruent cues) or different ones (incongruent cues)...
October 1, 2016: Cortex; a Journal Devoted to the Study of the Nervous System and Behavior
Ryan Eshleman, Rahul Singh
BACKGROUND: Adverse drug events (ADEs) constitute one of the leading causes of post-therapeutic death and their identification constitutes an important challenge of modern precision medicine. Unfortunately, the onset and effects of ADEs are often underreported complicating timely intervention. At over 500 million posts per day, Twitter is a commonly used social media platform. The ubiquity of day-to-day personal information exchange on Twitter makes it a promising target for data mining for ADE identification and intervention...
October 6, 2016: BMC Bioinformatics
Shashanka Ubaru, Abd-Krim Seghouane, Yousef Saad
This letter considers the problem of dictionary learning for sparse signal representation whose atoms have low mutual coherence. To learn such dictionaries, at each step, we first updated the dictionary using the method of optimal directions (MOD) and then applied a dictionary rank shrinkage step to decrease its mutual coherence. In the rank shrinkage step, we first compute a rank 1 decomposition of the column-normalized least squares estimate of the dictionary obtained from the MOD step. We then shrink the rank of this learned dictionary by transforming the problem of reducing the rank to a nonnegative garrotte estimation problem and solving it using a path-wise coordinate descent approach...
October 20, 2016: Neural Computation
Florian Kattner, Christopher R Cox, C Shawn Green
While learning is often highly specific to the exact stimuli and tasks used during training, there are cases where training results in learning that generalizes more broadly. It has been previously argued that the degree of specificity can be predicted based upon the learning solution(s) dictated by the particular demands of the training task. Here we applied this logic in the domain of rule-based categorization learning. Participants were presented with stimuli corresponding to four different categories and were asked to perform either a category discrimination task (which permits learning specific rule to discriminate two categories) or a category identification task (which does not permit learning a specific discrimination rule)...
2016: PloS One
Marco Cavarzere
This paper focuses on the shift that occurred in the spatial representation of states in the eighteenth century. This shift will be considered as a combination of institutional reforms and of a new social awareness of space. A consideration of the case of the Italian Piedmont will demonstrate how "national" space was created through antiquarian research and how a larger political confrontation took place in the guise of a learned debate. The diverse accounts of Piedmontese history under examination all employed methods derived from previous ages, relying upon a concept of space as historically continuous, embedded in time immemorial...
2016: Journal of the History of Ideas
Rachel A Ryskin, Zhenghan Qi, Melissa C Duff, Sarah Brown-Schmidt
Verbs often participate in more than 1 syntactic structure, but individual verbs can be biased in terms of whether they are used more often with 1 structure or the other. For instance, in a sentence such as "Bop the bunny with the flower," the phrase "with the flower" is more likely to indicate an instrument with which to "bop," rather than which "bunny" to bop. Conversely, in a sentence such as "Choose the cow with the flower," the phrase "with the flower" is more likely to indicate which "cow" to choose. An open question is where these biases come from and whether they continue to be shaped in adulthood in a way that has lasting consequences for real-time processing of language...
October 20, 2016: Journal of Experimental Psychology. Learning, Memory, and Cognition
Krisztián A Kovács, Joseph O'Neill, Philipp Schoenenberger, Markku Penttonen, Damaris K Ranguel Guerrero, Jozsef Csicsvari
During hippocampal sharp wave/ripple (SWR) events, previously occurring, sensory input-driven neuronal firing patterns are replayed. Such replay is thought to be important for plasticity-related processes and consolidation of memory traces. It has previously been shown that the electrical stimulation-induced disruption of SWR events interferes with learning in rodents in different experimental paradigms. On the other hand, the cognitive map theory posits that the plastic changes of the firing of hippocampal place cells constitute the electrophysiological counterpart of the spatial learning, observable at the behavioral level...
2016: PloS One
Hideyuki Matsumoto, Ju Tian, Naoshige Uchida, Mitsuko Watabe-Uchida
Dopamine is thought to regulate learning from appetitive and aversive events. Here we examined how optogenetically-identified dopamine neurons in the lateral ventral tegmental area of mice respond to aversive events in different conditions. In low reward contexts, most dopamine neurons were exclusively inhibited by aversive events, and expectation reduced dopamine neurons' responses to reward and punishment. When a single odor predicted both reward and punishment, dopamine neurons' responses to that odor reflected the integrated value of both outcomes...
October 19, 2016: ELife
Dahan Anat, Reiner Miriam
The extensive use of gestures for human-human communication, independently of culture and language, suggests an underlying universal neural mechanism for gesture recognition. The mirror neuron system (MNS) is known to respond to observed human actions, and overlaps with self-action. The minimal cues needed for activation of the MNS for gesture recognition, facial expressions and bodily dynamics, is not yet defined. Using LED-point representations of gestures, we compared two types of brain activations: 1) in response to human recognizable vs non-recognizable motion and 2) in response to human vs non-human motion...
October 15, 2016: International Journal of Psychophysiology
Peng Jiang, Zhixin Hu, Jun Liu, Shanen Yu, Feng Wu
Big sensor data provide significant potential for chemical fault diagnosis, which involves the baseline values of security, stability and reliability in chemical processes. A deep neural network (DNN) with novel active learning for inducing chemical fault diagnosis is presented in this study. It is a method using large amount of chemical sensor data, which is a combination of deep learning and active learning criterion to target the difficulty of consecutive fault diagnosis. DNN with deep architectures, instead of shallow ones, could be developed through deep learning to learn a suitable feature representation from raw sensor data in an unsupervised manner using stacked denoising auto-encoder (SDAE) and work through a layer-by-layer successive learning process...
October 13, 2016: Sensors
Gabriel Marzinotto, José C Rosales, Mounîm A El-Yacoubi, Sonia Garcia-Salicetti, Christian Kahindo, Hélène Kerhervé, Victoria Cristancho-Lacroix, Anne-Sophie Rigaud
Characterizing age from handwriting (HW) has important applications, as it is key to distinguishing normal HW evolution with age from abnormal HW change, potentially triggered by neurodegenerative decline. We propose, in this work, an original approach for online HW style characterization based on a two-level clustering scheme. The first level generates writer-independent word clusters from raw spatial-dynamic HW information. At the second level, each writer's words are converted into a Bag of Prototype Words that is augmented by an interword stability measure...
2016: Computational and Mathematical Methods in Medicine
Renee E Shimizu, Allan D Wu, Barbara J Knowlton
Effective learning results not only in improved performance on a practiced task, but also in the ability to transfer the acquired knowledge to novel, similar tasks. Using a modified serial reaction time (RT) task, the authors examined the ability to transfer to novel sequences after practicing sequences in a repetitive order versus a nonrepeating interleaved order. Interleaved practice resulted in better performance on new sequences than repetitive practice. In a second study, participants practiced interleaved sequences in a functional MRI (fMRI) scanner and received a transfer test of novel sequences...
October 17, 2016: Behavioral Neuroscience
Xinpei Ma, Chun-An Chou, Hiroki Sayama, Wanpracha Art Chaovalitwongse
Many neuroscience studies have been devoted to understand brain neural responses correlating to cognition using functional magnetic resonance imaging (fMRI). In contrast to univariate analysis to identify response patterns, it is shown that multi-voxel pattern analysis (MVPA) of fMRI data becomes a relatively effective approach using machine learning techniques in the recent literature. MVPA can be considered as a multi-objective pattern classification problem with the aim to optimize response patterns, in which informative voxels interacting with each other are selected, achieving high classification accuracy associated with cognitive stimulus conditions...
September 2016: Brain Informatics
Xiaodong Zhang, Shasha Jing, Peiyi Gao, Jing Xue, Lu Su, Weiping Li, Lijie Ren, Qingmao Hu
Segmentation of infarcts at hyperacute stage is challenging as they exhibit substantial variability which may even be hard for experts to delineate manually. In this paper, a sparse representation based classification method is explored. For each patient, four volumetric data items including three volumes of diffusion weighted imaging and a computed asymmetry map are employed to extract patch features which are then fed to dictionary learning and classification based on sparse representation. Elastic net is adopted to replace the traditional L0-norm/L1-norm constraints on sparse representation to stabilize sparse code...
2016: Computational and Mathematical Methods in Medicine
Akihiro Eguchi, Simon M Stringer
As Rubin's famous vase demonstrates, our visual perception tends to assign luminance contrast borders to one or other of the adjacent image regions. Experimental evidence for the neuronal coding of such border-ownership in the primate visual system has been reported in neurophysiology. We have investigated exactly how such neural circuits may develop through visually-guided learning. More specifically, we have investigated through computer simulation how top-down connections may play a fundamental role in the development of border ownership representations in the early cortical visual layers V1/V2...
October 13, 2016: Neurobiology of Learning and Memory
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"