Our goal is to synthesize realistic underwater scenes with various fish species in different fish cages, which can be utilized to train computer vision models to automate fish counting task.

Ukrainian President Volodymyr Zelenskyy travelled to New York to address the United Nations General Assembly in person for the first time since Moscow began its full-scale invasion of his country in February 2022. Dressed in his trademark khaki green shirt, he urged member states to come together to oppose Russian aggression and stressed the need for a peace recognising Ukraine's territorial integrity. Here is the full text of Zelenskyy's speech from September 19. I welcome all who stand for common efforts! And I promise – being really united we can guarantee fair peace for all nations.

When I went to grad school, I didn't choose 3D face recognition because I was interested in biometrics. I wanted to do computer vision for cars, and the professor I wanted to work with had left the university. So I went to the Computer Vision Research Lab (CVRL), and I asked what research they had available. Most of their work at the time was biometrics, and 3D face sounded interesting. It could pay the bills and give me experience that would translate to autonomous vehicles.

Can machine learning help clean it up? A team of computer scientists spanning the globe think so. They've built a neural network that can seemingly classify tweets into four different categories: normal, aggressor, spam, and bully – aggressor being a deliberately harmful, derogatory, or offensive tweet; and bully being a belittling or hostile message. The aim is to create a system that can filter out aggressive and bullying tweets, delete spam, and allow normal tweets through. The boffins admit it's difficult to draw a line between so-called cyber-aggression and cyber-bullying.

In this paper, we consider the problem of reducing the bit error rate of flash-based solid state drives (SSDs) when cells are subject to inter-cell interference (ICI). By observing that the outputs of adjacent victim cells can be correlated due to common aggressors, we propose a novel channel model to accurately represent the true flash channel. This model, equivalent to a finite-state Markov channel model, allows the use of the sum-product algorithm to calculate more accurate posterior distributions of individual cell inputs given the joint outputs of victim cells. These posteriors can be easily mapped to the log-likelihood ratios that are passed as inputs to the soft LDPC decoder. When the output is available with high precision, our simulation showed that a significant reduction in the bit-error rate can be obtained, reaching $99.99\%$ reduction compared to current methods, when the diagonal coupling is very strong. In the realistic case of low-precision output, our scheme provides less impressive improvements due to information loss in the process of quantization. To improve the performance of the new detector in the quantized case, we propose a new iterative scheme that alternates multiple times between the detector and the decoder. Our simulations showed that the iterative scheme can significantly improve the bit error rate even in the quantized case.

Abstract--Violence is an epidemic in Brazil and a problem on the rise worldwide. Mobile devices provide communication technologies which can be used to monitor and alert about violent situations. However, current solutions, like panic buttons or safe words, might increase the loss of life in violent situations. We propose an embedded artificial intelligence solution, using natural language and speech processing technology, to silently alert someone who can help in this situation. The corpus used contains 400 positive phrases and 800 negative phrases, totaling 1,200 sentences which are classified using two well-known extraction methods for natural language processing tasks: bag-of-words and word embeddings and classified with a support vector machine. We describe the proof-of-concept product in development with promising results, indicating a path towards a commercial product. More importantly we show that model improvements via word embeddings and data augmentation techniques provide an intrinsically robust model. The final embedded solution also has a small footprint of less than 10 MB.

Deep learning applies layers of hierarchical hidden variables to capture these interactions and nonlinearities. The theoretical roots lie in the Kolmogorov-Arnold representation theorem (Arnold, 1957; Kolmogorov, 1957) of multivariate functions, which states that any continuous multivariate function can be expressed as a superposition of continuous univariate semi-affine functions. This remarkable result has direct consequences for statistical modeling as a nonparametric pattern matching algorithm. Deep learning relies on pattern matching via its layers of univariate semi-affine functions and can be applied to both regression and classification problems. Deep learners provide a nonlinear predictor in complex settings where the input space can be very high dimensional.