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

We consider the problems of speckle removal in radar images. The proposed filtering techniques make use of local DCT denoising based on adaptive thresholding or homomorphic transformation. Two-stage DT denoising procedure in combination with local statistic filtering are also introduced and analyzed. The effectiveness of the proposed speckle removal algorithms is demonstrated by means of numerical simulations.© (2001) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Local transform-based denoising for radar image processing

A novel bicepstrum-based strategy is suggested for moving target recognition and classification by ground surveillance Doppler radars. Bicepstral coefficients extracted from non-stationary backscattered radar signals are used as the information features in automatic target recognition (ATR) system for solving a problem of moving human recognition and classification. ATR performance is studied by using Gaussian mixture model (GMM) and maximum likelihood (ML) rule. Experimental results obtained by ground surveillance homodyne radar operating in millimeter range wavelengths and continuous mode are represented and discussed. Classifier performance is examined in real-life conditions for walking human and group of walking humans in vegetation clutter environment.

Moving target classification in ground surveillance radar ATR system by using novel bicepstral-based information features

Image Processing: Algorithms and Systems II

Images of different origin contain textures, and textural features in such regions are frequently employed in pattern recognition, image classification, information extraction, etc. Noise often present in analyzed images might prevent a proper solution of basic tasks in the aforementioned applications and is worth suppressing. This is not an easy task since even the most advanced denoising methods destroy texture in a more or less degree while removing noise. Thus, it is desirable to predict the filtering behavior before any denoising is applied. This paper studies the efficiency of texture image denoising for different noise intensities and several filter types under different visual quality criteria (quality metrics). It is demonstrated that the most efficient existing filters provide very similar results. From the obtained results, it is possible to generalize and employ the prediction strategy earlier proposed for denoising techniques based on the discrete cosine transform. Accuracy of such a predicti...

https://www.worldscientific.com/doi/pdf/10.1142/S0218001418600054

IS Texture Denoising Efficiency Predictable

In recently proposed cooperative overtaking assistance systems a video stream captured by a windshield-mounted camera in a vehicle is compressed and broadcast to the vehicle driving behind it, where it is displayed to the driver. It has been shown that this system can provide robust operation if video codec channel adaptation is undertaken by exploiting information from the cooperative awareness messages about any forthcoming increases in the multiple access channel load. In this letter we demonstrate the gains achievable in system performance when the video transmitter power control is also used.

Karen Egiazarian

Papers

Local transform-based denoising for radar image processing

Moving target classification in ground surveillance radar ATR system by using novel bicepstral-based information features

Image Processing: Algorithms and Systems II

IS Texture Denoising Efficiency Predictable

Power Control in See-Through Overtaking Assistance System