Yanping Huang,Rajesh P N Rao
Yanping Huang
Motivated by the growing evidence for Bayesian computation in the brain, we show how a two-layer recurrent network of Poisson neurons can perform both approximate Bayesian inference and learning for any hidden Markov model. The lower-layer ...
Published Erratum
Neural computation. 2016 Jun;28(6):1248. DOI:10.1162/NECO_e_00861 2016
A Novel Nonparametric Approach for Neural Encoding and Decoding Models of Multimodal Receptive Fields [0.03%]
一种新颖的多模态感受野神经编码和解码模型的非参数方法
Rahul Agarwal,Zhe Chen,Fabian Kloosterman et al.
Rahul Agarwal et al.
Pyramidal neurons recorded from the rat hippocampus and entorhinal cortex, such as place and grid cells, have diverse receptive fields, which are either unimodal or multimodal. Spiking activity from these cells encodes information about the...
1D Current Source Density (CSD) Estimation in Inverse Theory: A Unified Framework for Higher-Order Spectral Regularization of Quadrature and Expansion-Type CSD Methods [0.03%]
基于逆理论的一维电流源密度(CSD)估计：高阶谱正则化齐多项式和展开型CSD方法的统一框架
Pascal Kropf,Amir Shmuel
Pascal Kropf
Estimation of current source density (CSD) from the low-frequency part of extracellular electric potential recordings is an unstable linear inverse problem. To make the estimation possible in an experimental setting where recordings are con...
Nonlinear Memory Capacity of Parallel Time-Delay Reservoir Computers in the Processing of Multidimensional Signals [0.03%]
并行时间延迟蓄水池计算机处理多维信号的非线性记忆容量
Lyudmila Grigoryeva,Julie Henriques,Laurent Larger et al.
Lyudmila Grigoryeva et al.
This letter addresses the reservoir design problem in the context of delay-based reservoir computers for multidimensional input signals, parallel architectures, and real-time multitasking. First, an approximating reservoir model is presente...
Regularized Multitask Learning for Multidimensional Log-Density Gradient Estimation [0.03%]
正则化多任务学习在多维对数密度梯度估计中的应用
Ikko Yamane,Hiroaki Sasaki,Masashi Sugiyama
Ikko Yamane
Log-density gradient estimation is a fundamental statistical problem and possesses various practical applications such as clustering and measuring nongaussianity. A naive two-step approach of first estimating the density and then taking its...
Haruo Hosoya,Aapo Hyvärinen
Haruo Hosoya
In visual modeling, invariance properties of visual cells are often explained by a pooling mechanism, in which outputs of neurons with similar selectivities to some stimulus parameters are integrated so as to gain some extent of invariance ...
A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function [0.03%]
一个单隐层前馈神经网络（其隐层只有单一神经元）可以以任意精度逼近任何单变量函数
Namig J Guliyev,Vugar E Ismailov
Namig J Guliyev
The possibility of approximating a continuous function on a compact subset of the real line by a feedforward single hidden layer neural network with a sigmoidal activation function has been studied in many papers. Such networks can approxim...
Marc-Alexandre Côté,Hugo Larochelle
Marc-Alexandre Côté
We present a mathematical construction for the restricted Boltzmann machine (RBM) that does not require specifying the number of hidden units. In fact, the hidden layer size is adaptive and can grow during training. This is obtained by firs...
Hiroaki Sasaki,Yung-Kyun Noh,Gang Niu et al.
Hiroaki Sasaki et al.
Estimating the derivatives of probability density functions is an essential step in statistical data analysis. A naive approach to estimate the derivatives is to first perform density estimation and then compute its derivatives. However, th...