The blooming progress made in deep learning-based image restoration has been largely attributed to the availability of high-quality, large-scale datasets and advanced network structures. However, optimization functions such as L1 and L2 are still de facto. In this study, we propose to investigate new optimization functions to improve image restoration performance. Our key insight is that "random weight network can be acted as a constraint for training better image restoration networks". However, not all random weight networks are suitable as constraints.

The blooming progress made in deep learning-based image restoration has been largely attributed to the availability of high-quality, large-scale datasets and advanced network structures. However, optimization functions such as L 2 are still de facto. In this study, we propose to investigate new optimization functions to improve image restoration performance. Our key insight is that ``random weight network can be acted as a constraint for training better image restoration networks''. However, not all random weight networks are suitable as constraints.

Natural Language Processing (NLP) is a vital computational method for addressing language processing, analysis, and generation. NLP tasks form the core of many daily applications, from automatic text correction to speech recognition. While significant research has focused on NLP tasks for the English language, less attention has been given to Modern Standard Arabic and Dialectal Arabic. Globalization has also contributed to the rise of Code-Switching (CS), where speakers mix languages within conversations and even within individual words (intra-word CS). This is especially common in Arab countries, where people often switch between dialects or between dialects and a foreign language they master. CS between Arabic and English is frequent in Egypt, especially on social media. Consequently, a significant amount of code-switched content can be found online. Such code-switched data needs to be investigated and analyzed for several NLP tasks to tackle the challenges of this multilingual phenomenon and Arabic language challenges. No work has been done before for several integral NLP tasks on Arabic-English CS data. In this work, we focus on the Named Entity Recognition (NER) task and other tasks that help propose a solution for the NER task on CS data, e.g., Language Identification. This work addresses this gap by proposing and applying state-of-the-art techniques for Modern Standard Arabic and Arabic-English NER. We have created the first annotated CS Arabic-English corpus for the NER task. Also, we apply two enhancement techniques to improve the NER tagger on CS data using CS contextual embeddings and data augmentation techniques. All methods showed improvements in the performance of the NER taggers on CS data. Finally, we propose several intra-word language identification approaches to determine the language type of a mixed text and identify whether it is a named entity or not.

The blooming progress made in deep learning-based image restoration has been largely attributed to the availability of high-quality, large-scale datasets and advanced network structures. However, optimization functions such as L1 and L2 are still de facto. In this study, we propose to investigate new optimization functions to improve image restoration performance. Our key insight is that random weight network can be acted as a constraint for training better image restoration networks''. However, not all random weight networks are suitable as constraints.

Machine learning (ML) is increasingly being used in critical decision-making software, but incidents have raised questions about the fairness of ML predictions. To address this issue, new tools and methods are needed to mitigate bias in ML-based software. Previous studies have proposed bias mitigation algorithms that only work in specific situations and often result in a loss of accuracy. Our proposed solution is a novel approach that utilizes automated machine learning (AutoML) techniques to mitigate bias. Our approach includes two key innovations: a novel optimization function and a fairness-aware search space. By improving the default optimization function of AutoML and incorporating fairness objectives, we are able to mitigate bias with little to no loss of accuracy. Additionally, we propose a fairness-aware search space pruning method for AutoML to reduce computational cost and repair time. Our approach, built on the state-of-the-art Auto-Sklearn tool, is designed to reduce bias in real-world scenarios. In order to demonstrate the effectiveness of our approach, we evaluated our approach on four fairness problems and 16 different ML models, and our results show a significant improvement over the baseline and existing bias mitigation techniques. Our approach, Fair-AutoML, successfully repaired 60 out of 64 buggy cases, while existing bias mitigation techniques only repaired up to 44 out of 64 cases.

Linear Regression is a seminal technique in statistics and machine learning, where the objective is to build linear predictive models between a response (i.e., dependent) variable and one or more predictor (i.e., independent) variables from a given dataset of n instances, where each instance is a set of values of the independent variables and the corresponding value of the dependent variable. One of the classical and widely used approaches is Ordinary Least Square Regression (OLS), where the objective is the minimize the average squared error between the predicted and actual value of the dependent variable. Another classical approach is Quantile Regression (QR), where the objective is to minimize the average weighted absolute error between the predicted and actual value of the dependent variable. QR (also known as "Median Regression" for the special case of the middle quantile), is less affected by outliers and thus statistically a more robust alternative to OLS [15, 18]. However, while there exist efficient algorithms for OLS, the state-of-art algorithms for QR require solving large linear programs with many variables and constraints. They can be solved using using interior point methods [24] which are weakly polynomial (i.e., in the arithmetic computation model the running time is polynomial in the number of bits required to represent the rational numbers in the input), or using Simplex-based exterior point methods which can have exponential time complexity in the worst case [10]. The main focus of our paper is an investigation of the computational complexity of Quantile Regression, and in particular, to design efficient strongly polynomial algorithms (i.e., in the arithmetic computation model the running time is polynomial in the number of rational numbers in the input) for various special cases of the problem.

Logic synthesis is one of the most important steps in design and implementation of digital chips with a big impact on final Quality of Results (QoR). For a most general input circuit modeled by a Directed Acyclic Graph (DAG), many logic synthesis problems such as delay or area minimization are NP-Complete, hence, no optimal solution is available. This is why many classical logic optimization functions tend to follow greedy approaches that are easily trapped in local minima that does not allow improving QoR as much as needed. We believe that Artificial Intelligence (AI) and more specifically Reinforcement Learning (RL) algorithms can help in solving this problem. This is because AI and RL can help minimizing QoR further by exiting from local minima. Our experiments on both open source and industrial benchmark circuits show that significant improvements on important metrics such as area, delay, and power can be achieved by making logic synthesis optimization functions AI-driven. For example, our RL-based rewriting algorithm could improve total cell area post-synthesis by up to 69.3% when compared to a classical rewriting algorithm with no AI awareness.

The amount of research produced each year by the Computational Intelligence (CI) community is astounding. One specific branch of CI is the ever-popular branch of Neural Networks. Neural Networks hit the mainstream because of their performance and the fascination to see how deep we could make the architectures. Deep learning seems to be synonymous with "Artificial Intelligence" these days, which has driven their acceptance. I was first exposed to deep learning when I was working on my master's thesis.

The term neural network doesn't need an introduction at all, only a few know the power of a neural net and a lot of people wanna learn this extraordinary tech. What are you going to read here then? Rather than discussing the types and applications of the neural network, I will be going through the seven mechanisms of the neural network that makes it powerful and versatile. This is an important question one has to answer before diving into this, if we unravel the caveats of a traditional program and replace it with some cool tweaks then we can call this a neural network. In traditional programming, we usually write the steps sequentially for it to run.