Hashing has been widely used for large-scale search due to its low storage cost and fast query speed. By using supervised information, supervised hashing can significantly outperform unsupervised hashing. Recently, discrete supervised hashing and deep hashing are two representative progresses in supervised hashing. On one hand, hashing is essentially a discrete optimization problem. Hence, util...

Visual cortex is traditionally viewed as a hierarchy of neural feature detectors, with neural population responses being driven by bottom-up stimulus features. Conversely, "predictive coding" models propose that each stage of the visual hierarchy harbors two computationally distinct classes of processing unit: representational units that encode the conditional probability of a stimulus and prov...

This paper proposes a feature extraction method for gesture recognition, which is based on higher order local autocorrelation (HLAC) of PARCOR images. To extract dominant information from a sequence of images, we apply linear prediction coding technique to the sequence of pixel values and PARCOR images are constructed from the PARCOR coe cients of the sequences of the pixel values. Then HLAC fe...

Synapses in real neural circuits can take discrete values, including zero (silent or potential) synapses. The computational role of zero synapses in unsupervised feature learning of unlabeled noisy data is still unclear, thus it is important to understand how the sparseness of synaptic activity is shaped during learning and its relationship with receptive field formation. Here, we formulate thi...

Short text differs from traditional documents in its shortness and sparseness. Feature extension can ease the problem of high sparseness in the vector space model, but it inevitably introduces noise. To resolve this problem, this paper proposes a high-frequency feature expansion method based on a latent Dirichlet allocation (LDA) topic model. High-frequency features are extracted from each cate...

We investigate when sparse coding of sensory inputs can improve performance in a classification task. For this purpose, we use a standard data set, the MNIST database of handwritten digits. We systematically study combinations of sparse coding methods and neural classifiers in a two-layer network. We find that processing the image data into a sparse code can indeed improve the classification pe...

Sparse Coding, a popular feature coding method, has shown superior performance in visual recognition tasks. Different pooling methods, such as average pooling and max pooling, are commonly employed after feature coding. However, it has not been explained clearly what characteristic accounts for the success of pooling method. In this paper, a new pooling method, namely protected pooling, is prop...

In this paper we propose a new feature extraction algorithm based on nonlinear prediction: the Neural Predictive Coding model which is an extension of the classical LPC one. This model is applied to speaker verification by the Arithmetic-Harmonic Sphericity (AHS) method. Two different initialization methods are proposed for the coding method based on the Neural Predictive Coding (NPC): classica...

This paper discusses the relation of theory and experiment in neuroscience exempliied by three assumptions often made in models of coherent activation in the cortex: basic feature-coding oscillators, phase-coding and global binding of whole objects. Apparently these assumptions are not very well supported by the experimental evidence. We propose that it is the single synchronized population-bur...

We provide evidence to the potential use of simple spoken tasks for automatic assessment of very early dementia. Timely detection of dementia is required for effective psychological treatment and to enable patients to participate in new drug therapy research. The technology enables automatic, cheap, remote and wide-scale screening of dementia, typically a costly and complex procedure. It can ai...