[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

Principal component analysis is one of the most important and powerful methods in chemometrics as well as in a wealth of other areas. This paper provides a description of how to understand, use, and interpret principal component analysis. The paper focuses on the use of principal component analysis in typical chemometric areas but the results are generally applicable.

/pdf/principal-component-analysis-1sba76ou47.pdf

Principal component analysis

Photoplethysmography and its application in clinical physiological measurement

PAPER on current memory circuit design (see Item 1 under References), which is published in IEEE TRANSACTIONS ON ELECTRON DEVICES, has drawn our attention. In this paper, a technique used to suppress the influence of charge injection in switched-current (SI) memory circuits, with an improvement in speed without relying on the matching of device characteristics, has been reported. The objective of this present note is to bring the attention of Lin and Shieh and the readers that the same technique with an identical circuit for an SI memory cell was published much earlier by Wang et al. in March 2000 (see Item 2 under References).

A Note on "A Novel Current Memory Circuit for AMOLEDs"

In recent times, image retrieval has garnered an increasing amount of interest due to the introduction of image datasets of significant size. Many methods have been suggested to retrieve images swiftly and accurately. However, the majority of these techniques are centered on the representation of the image. It is felt that alongside the representation of the image, smart storage is required that can rise to the demands of the task. A possible solution is to model human visual memory, retrieving images by imitating the brain's detection processes. This paper proposes a memory model that can be employed as smart memory for efficiently retrieving images based on image hashes. The memory model accepts hash code inputs derived from DWT and DCT transformations. The model is evaluated in terms of the memory capacity and the accuracy of the image retrieval. The results demonstrate that this model has a greater capacity and is significantly quicker than other types of memory models.

ExSDM: Novel Content-based Image Retrieval based on Sparse Distributed Memory Model

A formant estimation scheme combining the advantageous features of correlation and cepstral domains, which is capable of handling the adverse effect of observation noise was investigated. A residue-based least squares optimization technique based on a model-fitting approach was introduced in order to obtain formant frequencies from noisy observations. Simulations were carried out to estimate formant frequencies from synthetic and natural speech signals under noisy conditions. The human vocal-tract system was represented by a P-th order AR system with a transfer function. A formant frequency estimation scheme based on a new ramp cepstrum model was developed which is capable of efficiently handling the noisy environment. The once-repeated ACF was employed which can significantly reduce the effect of noise in the correlation domain. It was observed that the proposed method provides an accurate formant frequency estimate even at a low level of SNR.

/pdf/a-formant-frequency-estimator-for-noisy-speech-based-on-tqejd7sbho.pdf

A formant frequency estimator for noisy speech based on correlation and cepstrum

The design of ultralight-weight super-resolution convolutional neural networks capable of providing images with high visual quality is crucial in many real-world applications with limited power and storage capacity, such as mobile devices and portable cameras. In this paper, a new ultralight-weight super-resolution network, based on the idea of using multiresolution level feature interpolation in a residual framework, is developed. In the proposed network, the multiple resolution level interpolated features generated are fused and the resulting feature maps are added to the residual features obtained from a shallow convolutional neural network. The proposed network is applied to various benchmark datasets and is shown to outperform the state-of-the-art ultralight-weight image super-resolution networks existing in the literature.

MISNet: Multi-Resolution Level Feature Interpolating Ultralight-Weight Residual Image Super Resolution Network

Statistical image modeling has attracted great attention in the field of image denoising. In this work, a new image denoising method in the contourlet domain is introduced in which the contourlet coefficients of images are modeled by using the Bessel k-form prior. A noisy image is decomposed into a low frequency approximation sub-image and a series of high frequency detail sub-images at different scales and directions via the contourlet transform. To estimate the noise-free coefficients in detail subbands, a Bayesian estimator is developed utilizing the Bessel k-form distribution. In order to estimate the parameters of the distribution, a characteristic function-based technique is used. Simulation results on standard test images show improved performance both in visual quality and in terms of the peak signal-to-noise ratio and structural similarity index as compared to some of the existing denoising methods. The proposed method also achieves an excellent balance between noise suppression and details preservation.

M. Omair Ahmad

Papers

A Note on "A Novel Current Memory Circuit for AMOLEDs"

ExSDM: Novel Content-based Image Retrieval based on Sparse Distributed Memory Model

A formant frequency estimator for noisy speech based on correlation and cepstrum

MISNet: Multi-Resolution Level Feature Interpolating Ultralight-Weight Residual Image Super Resolution Network

Contourlet domain image denoising based on the Bessel k-form distribution