Loading...
  • 2017
  • Tentative / Confirmed Speakers == '''December 6th 2017''' * Speaker: Joel Makin * Time: 12:00 * Affiliation: UCSF * Host: Bruno * Status: tentative * Title: * Abstract: '''December 13, 2017''' * Speaker: Zhaoping Li * Time: 12:00 * Affiliation: UCL * Host: Bruno/Frederic Theunissen * Status: confirmed * Title: * Abstract: '''December 14, 2017''' * Speaker: * Time: 12:00 * Affiliation: * Host: Chris Hillar * Status: tentative * Title: Biologically plausible deep learning for recurrent spiking neural networks. (berkeley.edu)
  • 2016
  • Jan. 24, 2018''' * Speaker: Miguel Gredilla * Time: 12:00 * Affiliation: Vicarious * Host: Bruno * Status: confirmed * Title: * Abstract: '''TBD, sometime in the Fall''' * Speaker: Evangelos Theodorou * Time: TBD * Affiliation: GeorgiaTech * Host: Mike/Dibyendu Mandal * Status: planning * Title: TBD * Abstract: TBD '''TBD, 2016''' * Speaker: Alexander Stubbs * Time: 12:00 * Affiliation: UC Berkeley * Host: Bruno/Michael Levy * Status: tentative * Title: Could chromatic aberration allow for an alternative evolutionary pathway towards color vision? (berkeley.edu)
  • computation
  • Neural networks have been a subject of intense research activities over the past few decades due to their wide applications in many areas such as signal processing, pattern recognition, associative memories, parallel computation, and optimization solution. (hindawi.com)
  • Abstract The work described in this paper is part of a strategy to investigate useful architectures of parallel computation which encode speech knowledge into a speech recognition system to optimise its performance. (assta.org)
  • Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for a neural computation based on perturbations. (springer.com)
  • dynamics
  • Concepts from linear system theory were adapted to represent some aspects of neural dynamics, including solutions of simultaneous linear equations \(Y = AX\) using matrix theory, and concepts about cross-correlation. (scholarpedia.org)
  • Moreover, these task-optimized ConvRNNs matched the dynamics of neural activity in the primate visual system better than feedforward networks, suggesting a role for the brain's recurrent connections in performing difficult visual behaviors. (arxiv.org)
  • It expresses the dynamics of muscular activities in a straightforward way and takes advantage from the recurrent property. (springer.com)
  • 2018
  • article{broniatowski:2018a, title = {Weaponized Health Communication: Twitter Bots and Russian Trolls Amplify the Vaccine Debate}, author = {David A Broniatowski and Amelia M Jamison and SiHua Qi and Lulwah AlKulaib and Tao Chen and Adrian Benton and Sandra C Quinn and Mark Dredze}, year = {2018}, date = {2018-01-01}, journal = {American Journal of Public Health (AJPH)}, abstract = {Objectives. (jhu.edu)
  • Arana-Daniel N., Valdés-López J., Alanís A.Y., López-Franco C. (2018) Traversability Cost Identification of Dynamic Environments Using Recurrent High Order Neural Networks for Robot Navigation. (springer.com)
  • widespread
  • Abstract: Despite widespread success in deep learning, backpropagation has been criticized for its biological implausibility. (berkeley.edu)
  • Identification
  • Recurrent High Order Neural Networks (RHONN) trained with Extended Kalman Filter (EKF) are used to identify rough terrain traversability costs, and besides the good results in the identification tasks, we get the advantages of using a robust machine learning method such as RHONNs. (springer.com)
  • Abstract The study investigates the relationship between the perceptual identification of CV syllables and acoustic analyses of these sounds. (assta.org)
  • IONM may be used for identification of the RLN, aid in the dissection of the RLN, and be used to anticipate postoperative neural function. (springer.com)
  • pattern recognition
  • Anderson (1968) initially described his intuitions about neural pattern recognition using a spatial cross-correlation function. (scholarpedia.org)
  • This paper reviews various types of optical correlators and neural networks as applied to real-time optical pattern recognition for which some of the recent advances are included. (spie.org)
  • classification
  • We describe a robust gene expression-based molecular classification of GBM into Proneural, Neural, Classical, and Mesenchymal subtypes and integrate multidimensional genomic data to establish patterns of somatic mutations and DNA copy number. (nih.gov)
  • investigates
  • This paper investigates the profitability of a trading strategy, based on recurrent neural networks, that attempts to predict the direction-of-change of the market in the case of the NASDAQ composite index. (repec.org)
  • Our neuroscience research investigates the neural basis of movement preparation and generation using a combination of electro-/opto-physiological, behavioral, computational and theoretical techniques. (stanford.edu)
  • Our neuroengineering research investigates the design of high-performance and robust neural prostheses. (stanford.edu)
  • dynamical
  • As well known, the existence and nonexistence of solutions for nonlinear algebraic systems are very important since they can provide the necessary information on limiting behaviors of many dynamic systems, such as the discrete reaction-diffusion equations, the coupled map lattices, the compartmental systems, the strongly damped lattice systems, the complex dynamical networks, the discrete-time recurrent neural networks, and the discrete Turing models. (hindawi.com)
  • mesenchymal
  • Stem cell antibodies used included a series of three mesenchymal stem cell markers (CD44, CD105 and CD166) and five neural stem cell markers (CD15, CD29, CD56, CD133 and nestin). (aacrjournals.org)
  • signals
  • These systems translate neural activity from the brain into control signals for prosthetic devices, which can assist people with paralysis by restoring lost motor functions. (stanford.edu)
  • advances
  • Advances in Neural Information Processing Systems 25, pp. 1097-1105. (springer.com)
  • Despite advances in technology and understanding in spinal physiology, reoperation for symptomatic same-level recurrent stenosis continues to occur. (thejns.org)
  • thyroid surgery
  • Prospective study of vocal fold function after loss of the neuromonitoring signal in thyroid surgery: The International Neural Monitoring Study Group's POLT study. (lu.se)
  • architectures
  • We extended these design principles in an automated search over thousands of model architectures, which identified novel local recurrent cells and long-range feedback connections useful for object recognition. (arxiv.org)
  • robust
  • This paper is concerned with the robust dissipativity problem for interval recurrent neural networks (IRNNs) with general activation functions, and continuous time-varying delay, and infinity distributed time delay. (hindawi.com)
  • Abstract Acoustic sources are often occluded by other sounds, yet the strategies employed by the auditory system are remarkably robust against these intrusions. (assta.org)
  • Robust visual-textual sentiment analysis: when attention meets tree-structured recursive neural networks. (springer.com)
  • mechanism
  • Abstract: We present a mechanism by which organisms with only a single photoreceptor, which have a monochromatic view of the world, can achieve color discrimination. (berkeley.edu)
  • analysis
  • To receive news and publication updates for Abstract and Applied Analysis, enter your email address in the box below. (hindawi.com)
  • Therefore, many initial findings on the global dissipativity [ 18 , 22 - 30 ] or Lagrange stability [ 31 - 36 ] analysis of neural networks have been reported. (hindawi.com)
  • To date, an analysis of cost and heath state gain associated with revision lumbar surgery for recurrent same-level lumbar stenosis has yet to be described. (thejns.org)
  • Abstract The advantages of the application of a wavelet-transform analysis system to spoken materials are here discussed, with reference to some Italian examples. (assta.org)