5,104 Hits in 6.8 sec

Discriminating Two Types of Noise Sources using Cortical Representation and Dimension Reduction Technique

Shiva Sundaram, Shrikanth Narayanan
2007 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07  
In this paper we present results of our experiments on discriminating two types of noise sources. Particularly, we focus on machine-generated versus natural noise sources.  ...  To handle large tensor feature sets, we use a generalized discriminant analysis method to reduce the dimension.  ...  DISCUSSION AND CONCLUSION In this work, discrimination of two-types of noise sources: machine generated (such as vehicle noise, engine noise, printers, fax and telex machines etc.), versus other natural  ... 
doi:10.1109/icassp.2007.366654 dblp:conf/icassp/SundaramN07 fatcat:n5nl2qlnhrhzzlqtuiw4amysom

Encoding and Decoding Target Locations With Waves in the Turtle Visual Cortex

X. Du, B.K. Ghosh, P. Ulinski
2005 IEEE Transactions on Biomedical Engineering  
Sliding encoding windows were used to represent waves of activity as low dimensional temporal strands in an appropriate space.  ...  Assuming that the noise is colored provided a more reliable estimate than did the assumption of a white noise in the cortical output.  ...  A further reduction of the dimensionality of the wave is achieved by a second KL decomposition which maps the trajectory in A-space into a point in a low-dimension space called B-space.  ... 
doi:10.1109/tbme.2004.841262 pmid:15825858 fatcat:2qdrhovpanf6rhqzmgih5hzae4

Multimodal phenotypic axes of Parkinson's disease

Ross D. Markello, Golia Shafiei, Christina Tremblay, Ronald B. Postuma, Alain Dagher, Bratislav Misic
2021 npj Parkinson's Disease  
representation of heterogeneity in the sample compared to discrete biotypes.  ...  Finally, we identify a compact set of phenotypic axes that span the patient population, demonstrating that this continuous, low-dimensional projection of individual patients presents a more parsimonious  ...  Diffusion map embedding is a non-linear dimensionality reduction technique that finds a low-dimensional representation of graph structures 38, 39 .  ... 
doi:10.1038/s41531-020-00144-9 pmid:33402689 fatcat:l25domuxynbktolbtruinarhpe

Effects of categorization and discrimination training on auditory perceptual space

Frank H. Guenther, Fatima T. Husain, Michael A. Cohen, Barbara G. Shinn-Cunningham
1999 Journal of the Acoustical Society of America  
The results of these experiments are used to evaluate two neural network models of the perceptual magnet effect.  ...  This phenomenon is an example of acquired similarity and apparently has not been previously demonstrated for a category-relevant dimension.  ...  Sloan Foundation and the National Institute on Deafness and other Communication Disorders ͑NIDCD Grant No. R29 02852͒. Fatima Husain is supported by NIDCD Grant No. R29 02852.  ... 
doi:10.1121/1.428112 pmid:10573904 fatcat:un3aixan2rhrvkbg6h7w6vsaau

Ghosts in machine learning for cognitive neuroscience: Moving from data to theory

Thomas Carlson, Erin Goddard, David M. Kaplan, Colin Klein, J. Brendan Ritchie
2018 NeuroImage  
There are no easy solutions, but facing these issues squarely will provide a clearer path to understanding the nature of representation and computation in the human brain.  ...  Future progress in understanding brain function using these methods will require addressing a number of key methodological and interpretive challenges.  ...  That said, two other uses of dimensionality reduction may be more defensible (and these are often confused with data-driven extraction).  ... 
doi:10.1016/j.neuroimage.2017.08.019 pmid:28793239 fatcat:7nm43es45rcldjelaiqtpm3hma

Why neurons mix: high dimensionality for higher cognition

Stefano Fusi, Earl K Miller, Mattia Rigotti
2016 Current Opinion in Neurobiology  
Here we review the conceptual and theoretical framework that explains the importance of mixed selectivity and the experimental evidence that recorded neural representations are high-dimensional.  ...  This form of mixed selectivity plays an important computational role which is related to the dimensionality of the neural representations: high-dimensional representations with mixed selectivity allow  ...  However, these representations would be low dimensional, and therefore of limited use to a linear readout (see the Box for the upper bound on the number of dimensions).  ... 
doi:10.1016/j.conb.2016.01.010 pmid:26851755 fatcat:dk6cq44lgreyfhoeljplm7k5bq

Evaluating Feature Extraction Methods for Knowledge-based Biomedical Word Sense Disambiguation

Sam Henry, Clint Cuffy, Bridget McInnes
2017 BioNLP 2017  
We modify the vector representations in the 2-MRD WSD algorithm, and evaluate four dimensionality reduction methods: Word Embeddings using Continuous Bag of Words and Skip Gram, Singular Value Decomposition  ...  In this paper, we present an analysis of feature extraction methods via dimensionality reduction for the task of biomedical Word Sense Disambiguation (WSD).  ...  The goal of the dimensionality reduction techniques is to generate vector representations that reduce this type of noise.  ... 
doi:10.18653/v1/w17-2334 dblp:conf/bionlp/HenryCM17 fatcat:s27v3blmy5ebtepd73peqe54vm

Understanding Sensory Information Processing Through Simultaneous Multi-area Population Recordings

Elizabeth Zavitz, Nicholas S. C. Price
2019 Frontiers in Neural Circuits  
The goal of sensory neuroscience is to understand how the brain creates its myriad of representations of the world, and uses these representations to produce perception and behavior.  ...  In this article, we present an overview of some of the most promising analytical approaches for making inferences from population recordings in multiple brain areas, such as dimensionality reduction and  ...  Recording simultaneously from two or more neurons has advanced theories relating to how different types of ''noise,'' or inter-trial variability, affect stimulus discrimination (Zohary et al., 1994; Shadlen  ... 
doi:10.3389/fncir.2018.00115 pmid:30687020 pmcid:PMC6333685 fatcat:2n5dyt2zprfbpfxb6bzrxg34ly

Functional Data Analysis in brain imaging studies

T. Siva Tian
2010 Frontiers in Psychology  
These problems are dimension reduction (or feature extraction), spatial classification in fMRI studies, and the inverse problem in MEG studies.  ...  The development of functional brain imaging techniques in recent years made it possible to study the relationship between brain and mind over time.  ...  Another way consists of two parts: dimension reduction and classification. More specifically, first reduce the data dimension and then apply classification techniques to the reduced data.  ... 
doi:10.3389/fpsyg.2010.00035 pmid:21833205 pmcid:PMC3153754 fatcat:fqd36pvqvrefbhwlfrdntpb4ya

Robust Multifactor Speech Feature Extraction Based on Gabor Analysis

Qiang Wu, Liqing Zhang, Guangchuan Shi
2011 IEEE Transactions on Audio, Speech, and Language Processing  
To explore this property, we represent the speech signal by using a general higher order tensor and employ two-dimensional Gabor functions with different scales and directions to analyze the localized  ...  The objective of the sparse constraints is to preserve the statistical characteristic of clean speech data by finding projection matrices of speech subspaces and reduce the noise components which have  ...  Li and anonymous reviewers for their constructive comments on this paper.  ... 
doi:10.1109/tasl.2010.2070495 fatcat:ztrdicj57jfsvp6dw52rou62ui

Integrated morphometric, molecular, and clinical characterization of Parkinson's disease pathology [article]

Ross D. Markello, Golia Shafiei, Christina Tremblay, Ronald B. Postuma, Alain Dagher, Bratislav Misic
2020 bioRxiv   pre-print
representation of heterogeneity in the sample compared to discrete biotypes.  ...  Finally, we identify a compact set of phenotypic axes that span the patient population, demonstrating that this continuous, low-dimensional projection of individual patients presents a more parsimonious  ...  Diffusion map embedding is a nonlinear dimensionality reduction technique that finds a low-dimensional representation of graph structures [13, 44] .  ... 
doi:10.1101/2020.03.05.979526 fatcat:yinhglm7nzh2jlvijboz4xrwea

Learning in mammalian sensory cortex

2004 Current Opinion in Neurobiology  
Electrophysiological and neuroimaging studies of sensory systems in the cortex suggest that the changes underlying perceptual learning can occur in a variety of areas and are likely to involve multiple  ...  The rapid time course and ease with which some perceptual capabilities can improve suggest that learning is an integral part of normal perception.  ...  References and recommended reading Papers of particular interest, published within the annual period of review, have been highlighted as: of special interest of outstanding interest  ... 
doi:10.1016/j.conb.2004.07.003 pmid:15321073 fatcat:bobpx6vxkncvhidcofr5h6hmwy

A Survey: Early Detection of Alzheimer's Disease Using Different Techniques

Mareeswari S, Wiselin Jiji G
2015 International Journal on Computational Science & Applications  
The livelihood of the people that are diagnosed with AD. In this paper, we have discussed various imaging modalities, feature selection and extraction, segmentation and classification techniques.  ...  The use of PCA [32] within this work is justified not as a dimensional reduction technique but it is applied to the average images vector.  ...  It comprises of classification tasks, regression as well as modeling tools, dimension reduction techniques. It extended to regression problems naturally.  ... 
doi:10.5121/ijcsa.2015.5103 fatcat:6tnxx5zv6ngzpfbin5qtzkdn2e

Changes in Visual Cortex in Healthy Aging and Dementia [chapter]

Alyssa A. Brewer, Brian Barton
2016 Update on Dementia  
Measurements of disordered visual cortex in dementia patients may be possible early in the course of neurodegeneration and thus may be useful for improving early diagnosis of these devastating diseases  ...  This chapter reviews the differences in specific structural and functional characteristics of human visual cortex among young adults, healthy aging adults, and patients with dementia, with a primary focus  ...  Acknowledgements This work was supported in part by the National Institutes of Health Loan Repayment Program award #L30 EY019249 to A.A.B. and by the pilot grant to A.A.B. from the MIND Institute and Alzheimer's  ... 
doi:10.5772/64562 fatcat:at4daju7kvb4bhonjxjtayqo24

Pattern classification using principal components of cortical thickness and its discriminative pattern in schizophrenia

Uicheul Yoon, Jong-Min Lee, Kiho Im, Yong-Wook Shin, Baek Hwan Cho, In Young Kim, Jun Soo Kwon, Sun I. Kim
2007 NeuroImage  
We proposed pattern classification based on principal components of cortical thickness between schizophrenic patients and healthy controls, which was trained using a leave-one-out cross-validation.  ...  In particular, 40-70 principal components rearranged by a simple two-sample t-test which ranked the effectiveness of features were used for the best mean accuracy of simulated classification (frontal:  ...  Acknowledgment This work was supported by the research fund of Hanyang University (HY-2004-N).  ... 
doi:10.1016/j.neuroimage.2006.11.021 pmid:17188902 fatcat:cljcx2uufbc3hp7wkztvofarya
« Previous Showing results 1 — 15 out of 5,104 results