In this paper, a novel stochastic extra-step quasi-Newton method is developed to solve a class of nonsmooth nonconvex composite optimization problems. We assume that the gradient of the smooth part of the objective function can only be approximated by stochastic oracles. The proposed method combines general stochastic higher order steps derived from an underlying proximal type fixed-point equation with additional stochastic proximal gradient steps to guarantee convergence. Based on suitable bounds on the step sizes, we establish global convergence to stationary points in expectation and an extension of the approach using variance reduction techniques is discussed. Motivated by large-scale and big data applications, we investigate a stochastic coordinate-type quasi-Newton scheme that allows to generate cheap and tractable stochastic higher order directions. Finally, the proposed algorithm is tested on large-scale logistic regression and deep learning problems and it is shown that it compares favorably with other state-of-the-art methods.

ABSTRACT In this paper, we present a machine learning approach for estimating the number of incident wavefronts in a direction of arrival scenario. In contrast to previous works, a multilayer neural network with a cross-entropy objective is trained. Furthermore, we investigate an online training procedure that allows an adaption of the neural network to imperfections of an antenna array without explicitly calibrating the array manifold. We show via simulations that the proposed method outperforms classical model order selection schemes based on information criteria in terms of accuracy, especially for a small number of snapshots and at low signal-to-noise-ratios. Also, the online training procedure enables the neural network to adapt with only a few online training samples, if initialized by offline training on artificial data.

Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous research showed that effective learning in complex multi-agent systems demands for highly coordinated environment exploration among all the participating agents. Many researchers attempted to cope with this challenge through learning centralized value functions. However, the common strategy for every agent to learn their local policies directly often fail to nurture strong inter-agent collaboration and can be sample inefficient whenever agents alter their communication channels. To address these issues, we propose a new framework known as centralized training and exploration with decentralized execution via policy distillation. Guided by this framework and the maximum-entropy learning technique, we will first train agents' policies with shared global component to foster coordinated and effective learning. Locally executable policies will be derived subsequently from the trained global policies via policy distillation. Experiments show that our new framework and algorithm can achieve significantly better performance and higher sample efficiency than a cutting-edge baseline on several multi-agent DRL benchmarks.

Entity Coreference Resolution is the task of resolving all the mentions in a document that refer to the same real world entity and is considered as one of the most difficult tasks in natural language understanding. While in it is not an end task, it has been proved to improve downstream natural language processing tasks such as entity linking, machine translation, summarization and chatbots. We conducted a systematic a review of neural-based approached and provide a detailed appraisal of the datasets and evaluation metrics in the field. Emphasis is given on Pronoun Resolution, a subtask of Coreference Resolution, which has seen various improvements in the recent years. We conclude the study by highlight the lack of agreed upon standards and propose a way to expand the task even further.

Successfully navigating a complex environment to obtain a desired outcome is a difficult task, that up to recently was believed to be capable only by humans. This perception has been broken down over time, especially with the introduction of deep reinforcement learning, which has greatly increased the difficulty of tasks that can be automated. However, for traditional reinforcement learning agents this requires an environment to be able to provide frequent extrinsic rewards, which are not known or accessible for many real-world environments. This project aims to explore and contrast existing reinforcement learning solutions that circumnavigate the difficulties of an environment that provide sparse rewards. Different reinforcement solutions will be implemented over a several video game environments with varying difficulty and varying frequency of rewards, as to properly investigate the applicability of these solutions. This project introduces a novel reinforcement learning solution, by combining aspects of two existing state of the art sparse reward solutions.

Our research aims to develop interactive, social agents that can coach people to learn new tasks, skills, and habits. In this paper, we focus on coaching sedentary, overweight individuals (i.e., trainees) to exercise regularly. We employ adaptive goal setting in which the intelligent health coach generates, tracks, and revises personalized exercise goals for a trainee. The goals become incrementally more difficult as the trainee progresses through the training program. Our approach is model-based - the coach maintains a parameterized model of the trainee's aerobic capability that drives its expectation of the trainee's performance.

In simple words, Decision Tree Classifier is a Supervised Machine learning algorithm which is used for supervised classification problems. Under the hood in decision tree, each node asks a True or False question about one of the features and moves left or right with respect to the decision. You can learn more about Decision Tree from here. We are going to use a Machine Learning algorithms to find the patterns on the historical data of the students and classify their knowledge level, and for that we are going to write our own simple Decision Tree Classifier from scratch by using Python Programming Language. Though i am going to explain everything along the way, it will not be a basic level explanation.

The field of learning has evolved drastically over the years. With the advent of e-learning and learning management systems, the process of learning has gone beyond the traditional model of classroom training. Now it is possible for instructors and teachers to reach a wider, international audience through online courses hosted on cloud based LMS platforms. Students can access these courses from any place in the world at any time, by simply logging into their account using their login credentials. Although e-learning is a complete and self-sustainable medium for imparting knowledge, it also works well in conjunction with traditional classroom training.

Some years ago, at Gramener, we built a customer churn modeling solution for one of the largest global telecom operators. The machine learning solution predicted which of their customers would leave, one month before they stopped usage. In test pilots, the solution helped reduce customer churn by more than 56 percent compared to the earlier process. We were amazed at the impressive results and stellar accuracy. But the celebrations were a bit premature, for the solution was never used.

An international competition in artificial intelligence and robotics is set to take place in Dubai this week. The First Global Challenge aims to foster a culture of innovation and creativity in students across the UAE. The four-day event begins on October 24 at the Dubai Festival Arena and more than 1,500 young people are expected to attend. The theme of this year's contest is'Ocean Opportunities', with students competing to tackle issues from pollution to sustainability. "This event comes amidst repeated international calls to strengthen cooperation to find effective solutions to the issue of marine pollution by working on the adaptation of the latest technology," said Ahmed Al Falasi, Minister of State for Higher Education and Advanced Skills.