Despite the growing interest in continual learning, most of its contemporary works have been studied in a rather restricted setting where tasks are clearly distinguishable, and task boundaries are known during training. However, if our goal is to develop an algorithm that learns as humans do, this setting is far from realistic, and it is essential to develop a methodology that works in a task-free manner. Meanwhile, among several branches of continual learning, expansion-based methods have the advantage of eliminating catastrophic forgetting by allocating new resources to learn new data. In this work, we propose an expansion-based approach for task-free continual learning. Our model, named Continual Neural Dirichlet Process Mixture (CN-DPM), consists of a set of neural network experts that are in charge of a subset of the data. CN-DPM expands the number of experts in a principled way under the Bayesian nonparametric framework. With extensive experiments, we show that our model successfully performs task-free continual learning for both discriminative and generative tasks such as image classification and image generation.

To support human decision making with machine learning models, we often need to elucidate patterns embedded in the models that are unsalient, unknown, or counterintuitive to humans. While existing approaches focus on explaining machine predictions with real-time assistance, we explore model-driven tutorials to help humans understand these patterns in a training phase. We consider both tutorials with guidelines from scientific papers, analogous to current practices of science communication, and automatically selected examples from training data with explanations. We use deceptive review detection as a testbed and conduct large-scale, randomized human-subject experiments to examine the effectiveness of such tutorials. We find that tutorials indeed improve human performance, with and without real-time assistance. In particular, although deep learning provides superior predictive performance than simple models, tutorials and explanations from simple models are more useful to humans. Our work suggests future directions for human-centered tutorials and explanations towards a synergy between humans and AI.

Abstract-- The recent success of deep neural networks (DNNs) for function approximation in reinforcement learning has t rig-gered the development of Deep Reinforcement Learning (DRL) algorithms in various fields, such as robotics, computer gam es, natural language processing, computer vision, sensing sys tems, and wireless networking. Unfortunately, DNNs suffer from h igh computational cost and memory consumption, which limits th e use of DRL algorithms in systems with limited hardware resources. In recent years, pruning algorithms have demonstrated cons id-erable success in reducing the redundancy of DNNs in classifi cation tasks. However, existing algorithms suffer from a sign ificant performance reduction in the DRL domain. In this paper, we develop the first effective solution to the performance redu ction problem of pruning in the DRL domain, and establish a working algorithm, named Policy Pruning and Shrinking (PoPS), to tr ain DRL models with strong performance while achieving a compac t representation of the DNN. The framework is based on a novel iterative policy pruning and shrinking method that leverag es the power of transfer learning when training the DRL model. We present an extensive experimental study that demonstrates the strong performance of PoPS using the popular Cartpole, Luna r Lander, Pong, and Pacman environments. Finally, we develop an open source software for the benefit of researchers and devel opers in related fields. Deep reinforcement learning (DRL) algorithms have attracted much attention in recent years due to their capabili ty to provide a good approximation of the objective value in decision making tasks while dealing with very large state an d action spaces. In contrast to classic reinforcement learni ng methods that perform well for small-size models but perform poorly for large-scale models, DRL combines a deep neural network (DNN) with reinforcement learning for overcoming this issue. The DNN is used to map from states to actions in large-scale models so as to yield a policy that maximizes the objective value. In DeepMind's recently published Natu re paper [1], [2], a DRL algorithm was developed to teach computers how to play Atari games directly from the on-scree n Personal use of this material is permitted. Dor Livne and Kobi Cohen are with the School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Shev a 8410501 Israel. This work was supported in part by the U.S.-Israel Binationa l Science Foundation (BSF) under grant 2017723, and by the Cyber Secur ity Research Center at Ben-Gurion University of the Negev under grant 076 /16.

Algorithmic fairness in decision-making has been studied extensively in static settings where one-shot decisions are made on tasks such as classification. However, in practice most decision-making processes are of a sequential nature, where decisions made in the past may have an impact on future data. This is particularly the case when decisions affect the individuals or users generating the data used for future decisions. In this survey, we review existing literature on the fairness of data-driven sequential decision-making. We will focus on two types of sequential decisions: (1) past decisions have no impact on the underlying user population and thus no impact on future data; (2) past decisions have an impact on the underlying user population and therefore the future data, which can then impact future decisions. In each case the impact of various fairness interventions on the underlying population is examined.

With the rapid development of online education system, knowledge tracing which aims at predicting students' knowledge state is becoming a critical and fundamental task in personalized education. Traditionally, existing methods are domain-specified. However, there are a larger number of domains (e.g., subjects, schools) in the real world and the lacking of data in some domains, how to utilize the knowledge and information in other domains to help train a knowledge tracing model for target domains is increasingly important. We refer to this problem as domain adaptation for knowledge tracing (DAKT) which contains two aspects: (1) how to achieve great knowledge tracing performance in each domain. (2) how to transfer good performed knowledge tracing model between domains. To this end, in this paper, we propose a novel adaptable framework, namely adaptable knowledge tracing (AKT) to address the DAKT problem. Specifically, for the first aspect, we incorporate the educational characteristics (e.g., slip, guess, question texts) based on the deep knowledge tracing (DKT) to obtain a good performed knowledge tracing model. For the second aspect, we propose and adopt three domain adaptation processes. First, we pre-train an auto-encoder to select useful source instances for target model training. Second, we minimize the domain-specific knowledge state distribution discrepancy under maximum mean discrepancy (MMD) measurement to achieve domain adaptation. Third, we adopt fine-tuning to deal with the problem that the output dimension of source and target domain are different to make the model suitable for target domains. Extensive experimental results on two private datasets and seven public datasets clearly prove the effectiveness of AKT for great knowledge tracing performance and its superior transferable ability.

Stuart Russell is a distinguished artificial intelligence researcher, a Professor of Computer Science at the University of California, Berkeley, an Adjunct Professor of Neurological Surgery at the University of California, San Francisco, and leads the Center for Human-Compatible Artificial Intelligence at UC Berkeley. Along with Peter Norvig, Stuart is the author of Artificial Intelligence: A Modern Approach, the most widely used textbook on artificial intelligence. In his most recent book, Human Compatible: AI and the Problem of Control, Stuart proposes a fundamentally new approach to developing AI. In this interview, Stuart warns that AI is reshaping society in unintended ways. For example, social media content selection algorithms that choose what individuals watch and read do not even know that human beings exist. As AI becomes more capable, he suggests that we are going to see bigger failures unless we change the way we think about AI altogether. Stuart argues that to ensure AI is provably beneficial for human beings, we must design machines to be inherently uncertain about human preferences. This way, we can ensure they are humble, altruistic, and committed to pursuing our objectives even as they set their own goals. We also discuss why AI needs regulation similar to civil engineering and medicine, the impact AI is going to make over the next decade, autonomous vehicles, and a variety of other topics.

One of the popular open-source libraries in machine learning, TensorFlow provides a suitable abode with essential tools for ML researchers and developers in order to perform SOTA machine learning applications. According to a survey, this library is one of the most loved deep learning frameworks. In this article, we list down 10 free resources to learn TensorFlow in 2020. About: Advanced Machine Learning (ML) with TensorFlow on Google Cloud Platform Specialization is a course in Coursera offered by Google Cloud. This course is a little advanced for beginners and is meant for those who already entered the machine learning arena. In this course, one can learn the hands-on experience in optimising, deploying, and scaling production ML models of various types.

Recently, I read yet another article in Harvard Business Review about the potential for Artificial Intelligence (AI) and Big Data (BD) to revolutionize an industry, in this case that of education. After all, using computers in the classroom to aid in the acquisition of knowledge and skill has been a thing for some time now. So what this articles offered is a prediction of next-level impact. Again, a theme with which I've become quite familiar in the pages of this journal in recent years. That as I read, it hit me: virtually everything that the author, renowned AI expert Lasse Rouhiainen, suggested could be equally applied to the financial advisory/planning profession.

Data science is an interdisciplinary field of scientific methods, processes, algorithms & systems to extract knowledge or insights from data in various forms, structured or unstructured, similar to data mining. Data science Training Hyderabad is an interdisciplinary field of scientific methods, processes, algorithms, and systems to extract knowledge or insights from data in various forms, structured or unstructured, similar to data mining. Data science is a "concept to unify statistics, data analysis, machine learning & their related methods" in order to "understand & analyze actual phenomena" with data. It employs techniques and theories drawn from many fields within the broad areas of mathematics, statistics, information science, and computer science, in particular from the subdomains of machine learning, data mining, databases, and visualization. Data Science Turing award winner Jim Gray imagined data science as a " fourth paradigm" of science (empirical, theoretical, computational and now data-driven) and asserted that " everything about science is changing because of the impact of information technology" and the data deluge.

Earlier this year, a Chinese technology executive published an opinion piece arguing that size is China's greatest asset in technology competition with the United States today. His argument was simple: Innovation in emerging technologies such as artificial intelligence is partly a function of absolute numbers of scientists and engineers, and, as China continues to expand its domestic talent pipeline, its strength in numbers will soon far exceed that of the United States. Many in Washington seem to agree. The White House's education strategy draws motivation from China's rapidly increasing number of university graduates. Experts lament the United States' dependence on international talent and draw analogies with Sputnik to call for crisis-level educational spending levels similar to those in the post-Sputnik era.