SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling
نویسندگان
چکیده
We present a novel probabilistic framework for a hierarchical extension of independent component analysis (ICA), with a particular motivation in neuroscientific data analysis and modeling. The framework incorporates a general subspace pooling with linear ICA-like layers stacked recursively. Unlike related previous models, our generative model is fully tractable: both the likelihood and the posterior estimates of latent variables can readily be computed with analytically simple formulae. The model is particularly simple in the case of complex-valued data since the pooling can be reduced to taking the modulus of complex numbers. Experiments on electroencephalography (EEG) and natural images demonstrate the validity of the method.
منابع مشابه
A Convolutional Neural Network based on Adaptive Pooling for Classification of Noisy Images
Convolutional neural network is one of the effective methods for classifying images that performs learning using convolutional, pooling and fully-connected layers. All kinds of noise disrupt the operation of this network. Noise images reduce classification accuracy and increase convolutional neural network training time. Noise is an unwanted signal that destroys the original signal. Noise chang...
متن کاملEvaluating Sparse Codes on Handwritten Digits
Sparse coding of visual information has been of interest to the neuroscientific community for many decades and it is widely recognised that sparse codes should exhibit a high degree of statistical independence, typically measured by the kurtosis of the response distributions. In this paper we extend work on the hierarchical temporal memory model by studying the suitability of the augmented spat...
متن کاملObject Recognition with Multi-Scale Pyramidal Pooling Networks
We present a Multi-Scale Pyramidal Pooling Network, featuring a novel pyramidal pooling layer at multiple scales and a novel encoding layer. Thanks to the former the network does not require all images of a given classification task to be of equal size. The encoding layer improves generalisation performance in comparison to similar neural network architectures, especially when training data is ...
متن کاملModeling Nonlinear Dependencies in Natural Images using Mixture of Laplacian Distribution
Capturing dependencies in images in an unsupervised manner is important for many image processing applications. We propose a new method for capturing nonlinear dependencies in images of natural scenes. This method is an extension of the linear Independent Component Analysis (ICA) method by building a hierarchical model based on ICA and mixture of Laplacian distribution. The model parameters are...
متن کاملSurgical treatment of internal carotid artery anterior wall aneurysm with extravasation during angiography--case report.
A 54-year-old female presented subarachnoid hemorrhage from an aneurysm arising from the anterior (dorsal) wall of the internal carotid artery (ICA). During four-vessel angiography, an extravasated saccular pooling of contrast medium emerged in the suprasellar area unrelated to any arterial branch. The saccular pooling was visualized in the arterial phase and cleared in the venophase during eve...
متن کامل