Filters








3,170 Hits in 5.3 sec

Interactive image data labeling using self-organizing maps in an augmented reality scenario

Holger Bekel, Gunther Heidemann, Helge Ritter
2005 Neural Networks  
After this acquisition phase, a Self-Organizing Map (SOM) is trained on the complete set of patches, using combinations of MPEG-7 features as a data representation.  ...  With very little effort, the user can compose a training set for a classifier, thus, unknown objects can be made known to the system.  ...  Fig. 8 . 8 Top: displayed best match examples of a SOM trained with 15000 steps with equal weighting of color and edge features.  ... 
doi:10.1016/j.neunet.2005.06.040 pmid:16112547 fatcat:5tyub3qobvcrzoja6civdmcuhm

Causal Learning by a Robot with Semantic-Episodic Memory in an Aesop's Fable Experiment [article]

Ajaz A. Bhat, Vishwanathan Mohan
2020 arXiv   pre-print
We address this question by re-enacting the Aesop's Fable task on a robot and present a) a brain-guided neural model of semantic-episodic memory; with b) four task-agnostic learning rules that compare  ...  expectations from recalled past episodes with the current scenario to progressively extract the hidden causal relations.  ...  While the former relates to the motor affordance of an object, the latter relates to motion planning details, and interested reader may refer to Bhat et al. (2017) for details related to motion planning  ... 
arXiv:2003.00274v1 fatcat:dkihvepbjbh4rnl6r4goqstotq

Page 75 of American Sportswear & Knitting Times Vol. 30, Issue 42 [page]

1961 American Sportswear & Knitting Times  
The pastel has yet to be created that would not blend with that setting. In planning a line of colors and styles, store windows should not be considered as an adver- tising after-thought.  ...  Colors for such motifs are more subdued with stress On masculine styling.  ... 

The Motion Picture as a Tool in Medical Education

Warren Sturgis
1962 Journal of the SMPTE  
And the attack time of 40 milliseconds with a variable threshold and variable release time of .3 to 7 seconds offers complete compressor flexibility and performance.  ...  Now you can have a compressor for every mike channel with this miniature low cost Fairchild Compact Compressor.. .no larger than a slide type attenuator (actual size 1 4 x 7 ~4 4 inches).  ...  Usually, as is true of the motion picture in medical education, both processes are concurrent. Initiation Historically, teaching medicine through motion pictures has been with us only a short time.  ... 
doi:10.5594/j15497 fatcat:w2gscvgnnrbxnc3mcj4mksjqka

Changes in balance coordination and transfer to an unlearned balance task after slackline training: a self-organizing map analysis

Ben Serrien, Erich Hohenauer, Ron Clijsen, Wolfgang Taube, Jean-Pierre Baeyens, Ursula Küng
2017 Experimental Brain Research  
The SOM analysis, followed by a k-means clustering and marginal homogeneity test, showed that the balance coordination pattern was significantly different between pre-and post-test for the slackline task  ...  The shift in balance coordination on the slackline could be characterized by an increase in range of motion and a decrease in velocity and frequency in nearly all degrees of freedom simultaneously.  ...  Compliance with ethical standards Conflict of interest All authors declare that they have no conflict of interest that may have biased the findings in this article.  ... 
doi:10.1007/s00221-017-5072-7 pmid:28831563 fatcat:pqa4eh6iybbu7bvmq4z4bh2cie

Film Library Additions

1956 Academic Medicine  
A complete delivery is shown, with pre-and post-delivery pro cedures shown in detail.  ...  This motion pic- ture record has been edited and som« explanatory film material added to form the present report.  ... 
doi:10.1097/00001888-195601000-00030 fatcat:ohj2acvjyvduviwiwflmnsgxhq

Online recognition of unsegmented actions with hierarchical SOM architecture

Zahra Gharaee
2020 Cognitive Processing  
The method uses self-organizing neural networks to build a three-layer cognitive architecture.  ...  The experiment results show that although the performance drops slightly in online experiments compared to the offline tests, the ability of the proposed architecture to deal with the unsegmented action  ...  In order to improve action recognition and segmentation performance, it is planned plan to design and implement a sliding window of the pattern vectors with variable size that is adapted to the actual  ... 
doi:10.1007/s10339-020-00986-4 pmid:32700120 fatcat:auabydm4czerti5hxkvsbtreeq

Action in Mind: A Neural Network Approach to Action Recognition and Segmentation [article]

Zahra Gharaee
2021 arXiv   pre-print
Thus the architecture presents a biological plausible approach with certain features such as topographic organization of the neurons, lateral interactions, semi-supervised learning and the ability to represent  ...  For each level of development the system is trained with the input data consisting of consecutive 3D body postures and tested with generalized input data that the system has never met before.  ...  By perceiving the actions of others we usually interpret them as intentional and we use this knowledge for a better understanding while interacting with others.  ... 
arXiv:2104.14870v1 fatcat:cp7gnx34jbdq5o45zbfmhlrhlm

Theta phase coding in a network model of the entorhinal cortex layer II with entorhinal-hippocampal loop connections

Jun Igarashi, Hatsuo Hayashi, Katsumi Tateno
2006 Cognitive Neurodynamics  
In this talk, I will begin with the useful behavior of NMF in EEG pattern classification, which plays a critical role in noninvasive brain computer interface (BCI).  ...  The firing phase with respect to the theta rhythm advances within a theta cycle when the animal traverses a place field [1, 2].  ...  CONCLUSION We designed an element circuit for implementing PLL neural networks using the pulse-modulation approach. We verified the fundamental operation of two coupled element circuits with HSPICE.  ... 
doi:10.1007/s11571-006-9003-8 pmid:19003510 pmcid:PMC2267667 fatcat:avihqfr6a5e7tm43lythi27n3a

Cognitive Development in Partner Robots for Information Support to Elderly People

Akihiro Yorita, Naoyuki Kubota
2011 IEEE Transactions on Autonomous Mental Development  
Human interaction based on gestures is quite important to the expression of natural communication, and the meaning of gestures can be understood through intentional interactions with a human.  ...  The experimental results show that the proposed method can refine the relationships among this varied perceptual information that can then inform an updated relationship to natural communication with a  ...  Fig. 13(c) shows the reference vectors of SOM that are learned through the interaction with the subject. A.  ... 
doi:10.1109/tamd.2011.2105868 fatcat:dlxzzetfhfh27mmwdolctxhhva

Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps

Martin Stetter, Elmar W. Lang, Jianli Liu
2021 Computational Intelligence and Neuroscience  
After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment's future and use those for action planning.  ...  For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment.  ...  Traces with same colors correspond to the same simulation run.  ... 
doi:10.1155/2021/5590445 pmid:34804145 pmcid:PMC8604601 fatcat:o5odao4rnzaaxpvjhhikopwbnu

Learning intuitive physics and one-shot imitation using state-action-prediction self-organizing maps [article]

Martin Stetter, Elmar W. Lang
2021 arXiv   pre-print
After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment's future, and use those for action planning.  ...  For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment.  ...  Traces with same colors correspond to the same simulation run.  ... 
arXiv:2007.01647v3 fatcat:wrv62evc25b4rbzlgu7b6j2zjm

A Multimodal Connectionist Architecture for Unsupervised Grounding of Spatial Language

Michal Vavrečka, Igor Farkaš
2013 Cognitive Computation  
The visual scene is represented by several self-organizing maps (SOMs) and the auditory description is processed by a Recursive SOM that learns to topographically represent sequences.  ...  Primary representations from the first layer are unambiguously integrated in a multimodal module (implemented by SOM or "neural gas" algorithms) in the second layer.  ...  This problem was coined in literature as the (visual) binding problem, that is, a process of linking together the attributes (color, form, motion, size, and location) of a perceptual object.  ... 
doi:10.1007/s12559-013-9212-5 fatcat:56vruvqynjbi5duvlyakhnmncy

Sub-goal based Robot Visual Navigation through Sensorial Space Tesselation

George Palamas, J. Andrew Ware Andrew
2013 International Journal of Advanced Research in Artificial Intelligence (IJARAI)  
Initially a graph based world representation is used to build a map, prior to navigation, through an appearance based scheme using only features associated with color information.  ...  In this paper, we propose an evolutionary cognitive architecture to enable a mobile robot to cope with the task of visual navigation.  ...  as a SOM.  ... 
doi:10.14569/ijarai.2013.021106 fatcat:6eqnvhx3zjdypoypwboxua4w6y

Scene Description using Scale-Invariant Features for Mobile Robot Localization

Masaki ISHII, Yuya SASAKI
2014 International Journal of the Society of Materials Engineering for Resources  
This paper proposes a method of using special image information as a new feature of environmental mapping.  ...  We programmed a mobile robot to construct an environmental map using the information obtained from a laser range finder and rotary encoders.  ...  Based on the above findings, we believe that the combination of SURF and BoVW is effective in the expression of a scene, and a robot localizes its own position using only image information.  ... 
doi:10.5188/ijsmer.20.219 fatcat:puruufg6szeixfraidmcwd67q4
« Previous Showing results 1 — 15 out of 3,170 results