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

(b) Write out the equations for the time dependence of ρ11, ρ22, ρ12 and ρ21 assuming that a light field interaction V = -μ12Ee iωt + c.c. couples only levels |1> and |2>, and that the excited levels exhibit spontaneous decay. (8 marks) (c) Under steady-state conditions, find the ratio of populations in states |2> and |3>. (3 marks) (d) Find the slowly varying amplitude ̃ ρ 12 of the polarization ρ12 = ̃ ρ 12e iωt . (6 marks) (e) In the limiting case that no decay is possible from intermediate level |3>, what is the ground state population ρ11(∞)? (2 marks) 2. (15 marks total) In a 2-level atom system subjected to a strong field, dressed states are created in the form |D1(n)> = sin θ |1,n> + cos θ |2,n-1> |D2(n)> = cos θ |1,n> sin θ |2,n-1>

The Quantum Theory of Light

Mathematical Handbook for Scientists and Engineers

Neural networks

IEEE Transactions on Neural Networks

Optical 3D laser measurement system for navigation of autonomous mobile robot

Breaking text-based CAPTCHAs with variable word and character orientation

In this paper an approach to detect smoke columns from outdoor forest video sequences is proposed. The approach follows three basic steps. The first step is an image pre-processing block which resizes the image by applying a bicubic interpolation algorithm. The image is then transformed to its intensity values with a gray-scale transformation and finally the image is grouped by common areas with an image indexation. The second step consists of a smoke detection algorithm which performs a stationary wavelet transform (SWT) to remove high frequencies on horizontal, vertical, and diagonal details. The inverse SWT is then implemented and finally the image is compared to a non-smoke scene in order to determine the possible regions of interest (ROI). In order to reduce the number of false alarms, the final step of the proposed approach consists on a smoke verification algorithm, which determines whether the ROI is increasing its area or not. These results are combined to reach a final decision for detecting a smoke column on a sequence of static images from an outdoor video. Experimental results show that multi-resolution wavelet analysis is more accurate than the traditional low-pass filters on this application.

Wavelet-based smoke detection in outdoor video sequences

In this paper we present a novel approach for automatic segmentation and recognition of reCAPTCHA in Web sites. It is based on CAPTCHA image preprocessing with character alignment, morphological segmentation with three-color bar character encoding and heuristic recognition. The original proposal consists in exploiting three-color bar code for characters in CAPTCHA for their robust segmentation with presence of random collapse overlapping letters and distortions by particular patterns of waving rotation. Additionally, a novel implementation of SVM-based learning classifier for recognition of combinations of characters in training corpus has been proposed that permits to increment more than twice the recognition success rate without time extension of system response. The main goal of this research is to reduce vulnerability of CAPTCHA from spam and frauds as well as to provide a novel approach for recognizing either handwritten or degraded and damaged texts in ancient manuscripts. Our designed framework implementing the proposed approach has been tested in real-time applications with sites used CAPTCHAS achieving segmentation success rate about of 82% and recognition success rate about of 94%.

/pdf/breaking-recaptchas-with-unpredictable-collapse-heuristic-34a9waqgcu.pdf

Breaking reCAPTCHAs with unpredictable collapse: heuristic character segmentation and recognition

We present a taxonomy of the Artificial Intelligence (AI) methods currently applied for algorithmic music composition. The area known as algorithmic music composition concerns the research on processes of composing music pieces automatically by a computer system. The use of AI for algorithmic music consists on the application of AI techniques as the main tools for the composition generation. There are several models of AI used in music composition such as: heuristics in evolutionary algorithms, neural networks, stochastic methods, generative models, agents, decision trees, declarative programming and grammatical representation. In this survey we present the trending in techniques for automatic music composition. We summarized several research projects of the last seven years and highlight the directions of music composition based on AI techniques.

Oleg Starostenko

Papers

Optical 3D laser measurement system for navigation of autonomous mobile robot

Breaking text-based CAPTCHAs with variable word and character orientation

Wavelet-based smoke detection in outdoor video sequences

Breaking reCAPTCHAs with unpredictable collapse: heuristic character segmentation and recognition

Algoritmic music composition based on artificial intelligence: A survey