Neural Computation
Papers 3649
1 page of 365 pages (3,649 results)
As a training and analysis strategy for convolutional neural networks (CNNs), we slice images into tiled segments and use, for training and prediction, segments that both satisfy an information cri...
2 CitationsSource
#1Mengyu Tu (NYU: New York University)
#2Ruohe Zhao (NYU: New York University)H-Index: 1
Last. Zhe Chen (NYU: New York University)H-Index: 56
view all 5 authors...
Large-scale fluorescence calcium imaging methods have become widely adopted for studies of long-term hippocampal and cortical neuronal dynamics. Pyramidal neurons of the rodent hippocampus show spatial tuning in freely foraging or head-fixed navigation tasks. Development of efficient neural decoding methods for reconstructing the animal's position in real or virtual environments can provide a fast readout of spatial representations in closed-loop neuroscience experiments. Here, we develop an eff...
#1Masaaki Takada (Graduate University for Advanced Studies)
#2Taiji Suzuki (UTokyo: University of Tokyo)H-Index: 27
Last. Hironori Fujisawa (Graduate University for Advanced Studies)H-Index: 1
view all 3 authors...
Sparse regularization such as l1 regularization is a quite powerful and widely used strategy for high-dimensional learning problems. The effectiveness of sparse regularization has been supported practically and theoretically by several studies. However, one of the biggest issues in sparse regularization is that its performance is quite sensitive to correlations between features. Ordinary l1 regularization selects variables correlated with each other under weak regularizations, which results in d...
#1Terry Elliott (University of Southampton)H-Index: 16
Models of associative memory with discrete state synapses learn new memories by forgetting old ones. In contrast to non-integrative models of synaptic plasticity, models with integrative, filter-based synapses exhibit an initial rise in the fidelity of recall of stored memories. This rise to a peak is driven by a transient process and is then followed by a return to equilibrium. In a series of papers, we have employed a first passage time (FPT) approach to define and study memory lifetimes, incr...
#1Weishun Zhong (U of C: University of Chicago)H-Index: 1
#2Zhiyue Lu (U of C: University of Chicago)H-Index: 3
Last. Arvind Murugan (U of C: University of Chicago)H-Index: 13
view all 4 authors...
Continuous attractors have been used to understand recent neuroscience experiments where persistent activity patterns encode internal representations of external attributes like head direction or spatial location. However, the conditions under which the emergent bump of neural activity in such networks can be manipulated by space and time-dependent external sensory or motor signals are not understood. Here, we find fundamental limits on how rapidly internal representations encoded along continuo...
#1Michael C. Burkhart (Brown University)H-Index: 3
#2David M. Brandman (Dal: Dalhousie University)H-Index: 3
Last. Matthew T. Harrison (Brown University)H-Index: 13
view all 5 authors...
The Kalman filter provides a simple and efficient algorithm to compute the posterior distribution for state-space models where both the latent state and measurement models are linear and gaussian. ...
#1Shreya Saxena (MIT: Massachusetts Institute of Technology)H-Index: 4
#2Sridevi V. Sarma (Johns Hopkins University)H-Index: 15
Last. Munther A. Dahleh (MIT: Massachusetts Institute of Technology)H-Index: 46
view all 3 authors...
The ability to move fast and accurately track moving objects is fundamentally constrained by the biophysics of neurons and dynamics of the muscles involved. Yet the corresponding trade-offs between...
#1Manuel Ciba (Ciba: Ciba Specialty Chemicals)H-Index: 2
#2Robert BestelH-Index: 1
Last. Christiane ThielemannH-Index: 11
view all 9 authors...
As synchronized activity is associated with basic brain functions and pathological states, spike train synchrony has become an important measure to analyze experimental neuronal data. Many measures...
#1Jing Gao (DUT: Dalian University of Technology)H-Index: 3
#2Peng Li (DUT: Dalian University of Technology)H-Index: 13
Last. Jianing Zhang (DUT: Dalian University of Technology)
view all 4 authors...
With the wide deployments of heterogeneous networks, huge amounts of data with characteristics of high volume, high variety, high velocity, and high veracity are generated. These data, referred to ...
2 CitationsSource
#1Noah Frazier-LogueH-Index: 1
#2Stephen José Hanson (RU: Rutgers University)H-Index: 28
Multilayer neural networks have led to remarkable performance on many kinds of benchmark tasks in text, speech, and image processing. Nonlinear parameter estimation in hierarchical models is known ...
Top fields of study
Machine learning
Mathematical optimization
Models of neural computation
Artificial neural network