A proper understanding of the striking generalization abilities of deep neural networks presents an enduring puzzle. Recently, there has been a growing body of numerically-grounded theoretical work that has contributed important insights to the theory of learning in deep neural nets. There has also been a recent interest in extending these analyses to understanding how multitask learning can further improve the generalization capacity of deep neural nets. These studies deal almost exclusively with regression tasks which are amenable to existing analytical techniques. We develop an analytic theory of the nonlinear dynamics of generalization of deep neural networks trained to solve classification tasks using softmax outputs and cross-entropy loss, addressing both single task and multitask settings. We do so by adapting techniques from the statistical physics of disordered systems, accounting for both finite size datasets and correlated outputs induced by the training dynamics. We discuss the validity of our theoretical results in comparison to a comprehensive suite of numerical experiments. Our analysis provides theoretical support for the intuition that the performance of multitask learning is determined by the noisiness of the tasks and how well their input features align with each other. Highly related, clean tasks benefit each other, whereas unrelated, clean tasks can be detrimental to individual task performance.

-- Mammography is often used as the most common laboratory method for the detection of breast cancer, yet associated with the high cost and many side effects. M achine learning prediction as an alternative method has shown promising results. This paper present s a method based on a mul tilayer fuzzy expert system for the detection of breast cancer using an e xtreme learning machine (ELM) classification model integrated with radial basis function (RBF) kernel called ELM - RBF, considering the Wisconsin dataset . The performance of the propose d model is further compared with a l inear - SVM model. Furthermore, both models are studied in terms of criteria of accuracy, precision, sensitivity, specificity, validation, true positive rate (TPR), and false - negative rate (FNR). The ELM - RBF model for these criteria presents better performance compared to the SVM model . Breast cancer is among the most common disease of young women over the world [1 - 3]. Approximately 29.9% of mortality from can cer in women is due to breast cancer. The incidence of this disease is lower in developing countries than in developed countries, about 10% of women with breast cancer in Western countries.

Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. In particular, skin cancer classification models have achieved performance higher than trained expert dermatologists. However, no attempt has been made to evaluate the consistency in performance of machine learning models across populations with varying skin tones. In this paper, we present an approach to estimate skin tone in benchmark skin disease datasets, and investigate whether model performance is dependent on this measure. Specifically, we use individual typology angle (ITA) to approximate skin tone in dermatology datasets. We look at the distribution of ITA values to better understand skin color representation in two benchmark datasets: 1) the ISIC 2018 Challenge dataset, a collection of dermoscopic images of skin lesions for the detection of skin cancer, and 2) the SD-198 dataset, a collection of clinical images capturing a wide variety of skin diseases. To estimate ITA, we first develop segmentation models to isolate non-diseased areas of skin. We find that the majority of the data in the the two datasets have ITA values between 34.5{\deg} and 48{\deg}, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets. We also find no measurable correlation between performance of machine learning model and ITA values, though more comprehensive data is needed for further validation.

Artificial Intelligence (AI) will impact every single industry in the next ten years, according to Peter DeBenedictus, CMO - Middle East and Africa, Microsoft. DeBenedictus was part of a panel discussion at the Arabian Business forum Success 2020 entitled: 'Embracing new technological innovations to deliver success'. He said: "There's not one single job or industry that will not be impacted by AI." He revealed that the jobs under threat include lawyers and radiologists as well as the more typical example of call centre operators. "Any job or task that is routine, repeatable and learnable by a machine, will disappear in the next five to ten years. "Think about accounting and audit.

When we hear technology we think of electronic gadgets and a hundred types of software. But the problems of the future are going to be more basic. Food, water, and shelter are important to talk about. They're essential to sustain human life and limited in availability. Moreover, the increasing population and concentration of population in major cities will possibly lead to scarcity unless we take due action.

Paull Allen who is Co-founder of Microsoft published results of experiment with great elephant's census around 2 years ago. This was an effort to count Savannah elephants in Africa. Between 2007 in 2014, Population of elephants was decrease by about the third and was about to vanish completely from some African countries. Researchers were able to use artificial intelligence technology to reverse this trend, which really help them to rewrite the rules for everything which we are doing for household appliances, through AI. Ability of artificial intelligence can help in finding patterns and gathering information which then further can be used to modify behaviour.

With conversational commerce mushrooming throughout the retail world, it surely must have the feel of déjà vu for the iconic 1-800-Flowers.com Founded in 1976 and branded with its workhorse 1-800-Flowers phone number in 1986, the company can point to its penchant for speaking directly to its customers as a reason for its longevity -- first through the phone and then across the internet. The process of conversational commerce uses remarkably intuitive technology tools such as voice messaging and chatbot applications to facilitate seamless interactions between brands and shoppers to drive transactions or trigger service. Voice protocols are emerging as the dominant technique fueling conversational commerce, notably voice assistants such as Apple Siri, Google Assistant and Amazon Alexa. In addition, text-enabled chatbots are proliferating to help consumers through human-like conversations.

Gartner, Inc. today revealed its top strategic predictions for 2020 and beyond. Gartner's top predictions examine how the human condition is being challenged as technology creates varied and ever-changing expectations of humans. "Technology is changing the notion of what it means to be human," said Daryl Plummer, distinguished vice president and Gartner Fellow. "As workers and citizens see technology as an enhancement of their abilities, the human condition changes as well. CIOs in end-user organizations must understand the effects of the change and reset expectations for what technology means."

The Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), the first graduate-level, research-based artificial intelligence (AI) university in the world, has received immediate interest from graduate students across the globe. So far, 3,200 students have started the application process, including 1,681 potential students in the last step of their application process and 234 completing their applications within the first week of the university's launch on October 16. The majority of applications were received from the UAE, Saudi Arabia, Algeria, Egypt, India, and China, a statement said. Dr Sultan Ahmed Al Jaber, UAE Minister of State and chairman of the MBZUAI board of trustees, said: "The level of interest in such a short time is a very encouraging sign. MBZUAI is attracting prospective students from around the world, affirming the UAE leadership's vision of investing in human potential and enabling societies through knowledge and education to find practical solutions to some of the biggest challenges in the world, and further establishing the UAE and Abu Dhabi as a global hub for innovation and higher education."

We consider the case of derivative-free algorithms for non-convex optimization, also known as zero order algorithms, that use only function evaluations rather than gradients. For a wide variety of gradient approximators based on finite differences, we establish asymptotic convergence to second order stationary points using a carefully tailored application of the Stable Manifold Theorem. Regarding efficiency, we introduce a noisy zero-order method that converges to second order stationary points, i.e avoids saddle points. Our algorithm uses only $\tilde{\mathcal{O}}(1 / \epsilon^2)$ approximate gradient calculations and, thus, it matches the converge rate guarantees of their exact gradient counterparts up to constants. In contrast to previous work, our convergence rate analysis avoids imposing additional dimension dependent slowdowns in the number of iterations required for non-convex zero order optimization.