We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

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

计量经济分析 = Econometric analysis

This paper studies near lossless JPEG image compression. A method of estimation of image regions masking ability (maximal level of distortions invisible for human visual system) using non-predictable energy of image regions is described. A novel method of zeroing quantized DCT coefficients of JPEG images to increase their compression ratio without introducing visible distortions is proposed. A numerical analysis of effectiveness of the proposed near lossless compression method using 300 noise free test images of TAMPERE17 database is carried out. It is shown that the proposed method provides an increase of compression ratio of JPEG images without visible distortions at about 1.35 times in average. Additionally, the proposed method results in decreasing of variability of compression ratio values for different images. It is shown that the proposed method increases minimal compression ratio for highly textured JPEG images from 1.1…1.5 times to 2 times. Carried out experiments demonstrated once again that the traditional PSNR metric does not correspond to human perception for this task.

Near Lossless JPEG Compression Based on Masking Effect of Non-predictable Energy of Image Regions

The invention relates to method for coding data in an electronic device. In the method a source text is obtained in the memory. At least one symbol in the source text is grouped in at least one symbol group based on the probability of said at least one symbol in the source text. A prefix and a suffix stream are formed using codewords for said at least one symbol. Each subsequent prefix pair in said prefix stream is concatenated to form a concatenated prefix stream. The concatenated prefix stream is set as a new source text in said memory and the coding procedure is repeated if the number of symbol groups among said at least one symbol group is less than or equal to a predefined threshold value.

Method for fast recursive coding in electronic devices

Let Ln2 equals L2 (R) X L2 (R) X ... X L2 (R)/n. It is shown how to construct a system of functions {(phi) k (x)} equals {(phi) k(1) (x), (phi) k(2) (x), ..., (phi) k(n) (x)} from Ln2 which satisfies the following conditions: (1) After normalization it forms a Riesz basis in Ln2; (2) For any given set of functions [f1(x), f2(x), ..., fn(x)] (summation) Ln2 the representations fj(x) equals (Sigma) /k ck (DOT) (phi) k(j) (x), x (summation) R, j equals 1,n, hold, where the coefficients ck are defined from {(phi) k (x)} and [f1(x), f2(x),..., fn(x)].© (2002) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Extension of the concept of wavelet to vector functions

A robust version of Lee local statistic filter able to effectively suppress the mixed multiplicative and impulse noise in images is proposed. The performance of the proposed modification is studied for a set of test images, several values of multiplicative noise variance, Gaussian and Rayleigh probability density functions of speckle, and different characteris-tics of impulse noise. The advantages of the designed filter in comparison to the conventional Lee local statistic filter and some other filters able to cope with mixed multiplicative+impulse noise are demonstrated.

Robust Lee local statistic filter for removal of mixed multiplicative and impulse noise

We consider the closed glottis interval determination problem from the point of view of getting a multiresolution signal representation and searching for maxima in successive scales Within this framework, an octave band decomposition, using half-band finite impulse response (FIR) filters is very promising, since those filters are less constrained than the orthogonal and biorthogonal wavelet filters A number of experiments with synthesized signals argue the superior performance of the multiresolution approach in comparison with the traditional covariance approaches

Karen Egiazarian

Papers

Near Lossless JPEG Compression Based on Masking Effect of Non-predictable Energy of Image Regions

Method for fast recursive coding in electronic devices

Extension of the concept of wavelet to vector functions

Robust Lee local statistic filter for removal of mixed multiplicative and impulse noise

A multiresolution approach to closed glottis interval determination