We study a system composed of multiple distinct service locations that aims to convince customers to join the system by providing information to customers. We cast the system's information design problem in the framework of Bayesian persuasion and describe centralized and decentralized signaling. We provide efficient methods for computing the system's optimal centralized and decentralized signaling mechanisms and derive a performance guarantee for decentralized signaling when the locations' states are independent. The guarantee states that the probability that a customer joins under optimal decentralized signaling is bounded below by the product of a strictly positive constant and the probability that a customer joins under optimal centralized signaling. The constant depends only on the number of service locations. We provide an example that shows that the constant cannot be improved. We consider an extension to more-general objectives for the system and establish that the same guarantee continues to hold. We also extend our analysis to systems where the locations' states are correlated, and again derive a performance guarantee for decentralized signaling in that setting. For the correlated setting, we prove that the guarantee's asymptotic dependence upon the number of locations cannot be substantially improved. A comparison of our guarantees for independent locations and for correlated locations reveals the influence of dependence on the performance of decentralized signaling.

Motivated by information sharing in online platforms, we study repeated persuasion between a sender and a stream of receivers where at each time, the sender observes a payoff-relevant state drawn independently and identically from an unknown distribution, and shares state information with the receivers who each choose an action. The sender seeks to persuade the receivers into taking actions aligned with the sender's preference by selectively sharing state information. However, in contrast to the standard models, neither the sender nor the receivers know the distribution, and the sender has to persuade while learning the distribution on the fly. We study the sender's learning problem of making persuasive action recommendations to achieve low regret against the optimal persuasion mechanism with the knowledge of the distribution. To do this, we first propose and motivate a persuasiveness criterion for the unknown distribution setting that centers robustness as a requirement in the face of uncertainty. Our main result is an algorithm that, with high probability, is robustly-persuasive and achieves $O(\sqrt{T\log T})$ regret, where $T$ is the horizon length. Intuitively, at each time our algorithm maintains a set of candidate distributions, and chooses a signaling mechanism that is simultaneously persuasive for all of them. Core to our proof is a tight analysis about the cost of robust persuasion, which may be of independent interest. We further prove that this regret order is optimal (up to logarithmic terms) by showing that no algorithm can achieve regret better than $\Omega(\sqrt{T})$.

A brain-inspired computer chip can run AI-powered image recognition operations 22 times faster than comparable commercial chips, and with 25 times the energy efficiency. The IBM NorthPole chip intertwines its computational capability with associated memory blocks that store information. This allows it to bypass the so-called the von Neumann bottleneck – named after computing pioneer John von Neumann – which describes how modern computers slow down while waiting on information exchanges between more separated compute and memory units. The melding of computation and memory was inspired by the way the human brain works. IBM had previously built a chip based on this idea called TrueNorth. But NorthPole transforms the technology into a digital architecture that is compatible with the silicon chip technology used in contemporary computers.

EDITOR'S NOTE: This is the first of Automotive News Canada's two-part look into artificial intelligence in the Canadian auto industry. Scanning an employee badge at a Martinrea International Inc. plant is no longer reserved for the front gates. Today, operators swipe into assembly equipment with their keycards, logging details about how well they have been trained, their experience on the machines and what output level they can achieve. Sifting through the evolving stream of data using artificial intelligence (AI) helps match the right operator to the right machine, said Ganesh Iyer, chief technology officer at the Toronto-based supplier. The process is one in a growing arsenal of AI tools aimed at improving speed and precision at automakers and parts suppliers.

Large scale machine learning and deep models are extremely data-hungry. Unfortunately, obtaining large amounts of labeled data is expensive, and training state-of-the-art models (with hyperparameter tuning) requires significant computing resources and time. Secondly, real-world data is noisy and imbalanced. As a result, several recent papers try to make the training process more efficient and robust. However, most existing work either focuses on robustness or efficiency, but not both. In this work, we introduce Glister, a GeneraLIzation based data Subset selecTion for Efficient and Robust learning framework. We formulate Glister as a mixed discrete-continuous bi-level optimization problem to select a subset of the training data, which maximizes the log-likelihood on a held-out validation set. Next, we propose an iterative online algorithm Glister-Online, which performs data selection iteratively along with the parameter updates and can be applied to any loss-based learning algorithm. We then show that for a rich class of loss functions including cross-entropy, hinge-loss, squared-loss, and logistic-loss, the inner discrete data selection is an instance of (weakly) submodular optimization, and we analyze conditions for which Glister-Online reduces the validation loss and converges. Finally, we propose Glister-Active, an extension to batch active learning, and we empirically demonstrate the performance of Glister on a wide range of tasks including, (a) data selection to reduce training time, (b) robust learning under label noise and imbalance settings, and (c) batch-active learning with several deep and shallow models. We show that our framework improves upon state of the art both in efficiency and accuracy (in cases (a) and (c)) and is more efficient compared to other state-of-the-art robust learning algorithms in case (b).

After creating tiny sensor backpacks for bees, researchers from the University of Washington have built a more advanced model for beetles. Dubbed "a GoPro for beetles," the robotic backpacks carry a tiny steerable camera that can stream video at 1 to 5 fps and pivot up to 60 degrees. On top of getting an interesting bugs-eye view of the world, the devices could power future biological studies and allow us to "explore novel environments," according to the team. The backpack was designed to be carried by two species: A "death-feigning" beetle and Pinacate beetle. Both of those have been observed carrying up to half a gram at a time.

Mumbai-based Qure.ai uses an artificial intelligence-powered solution to identify 24 different abnormalities in a chest X-ray, including ones indicative of a covid-19 infection. Built on Amazon Web Services (AWS) and trained using machine learning to detect pulmonary problems, including diseases like tuberculosis, the original solution has been repurposed by Qure for the ongoing pandemic. Given the global shortage of test kits, Qure's machine learning solution qXR can very quickly prioritize those who need to be tested immediately and those who need to be self-isolated, thus helping to maximise resource utilization. Since the launch of the covid-19 version in March, qXR has been deployed in over 40 sites globally, including Mumbai. The Municipal Corporation of Greater Mumbai (MCGM) has deployed this cost-effective and scalable solution to assist the front line critical healthcare professionals.

For many years, achievements and discoveries made by scientists are made aware through research papers published in appropriate journals or conferences. Often, established scientists and especially newbies are caught up in the dilemma of choosing an appropriate conference to get their work through. Every scientific conference and journal is inclined towards a particular field of research and there is a vast multitude of them for any particular field. Choosing an appropriate venue is vital as it helps in reaching out to the right audience and also to further one's chance of getting their paper published. In this work, we address the problem of recommending appropriate conferences to the authors to increase their chances of acceptance. We present three different approaches for the same involving the use of social network of the authors and the content of the paper in the settings of dimensionality reduction and topic modeling. In all these approaches, we apply Correspondence Analysis (CA) to derive appropriate relationships between the entities in question, such as conferences and papers. Our models show promising results when compared with existing methods such as content-based filtering, collaborative filtering and hybrid filtering.

Tweet classification has attracted considerable attention recently. Most of the existing work on tweet classification focuses on topic classification, which classifies tweets into several predefined categories, and sentiment classification, which classifies tweets into positive, negative and neutral. Since tweets are different from conventional text in that they generally are of limited length and contain informal, irregular or new words, so it is difficult to determine user intention to publish a tweet and user attitude towards certain topic. In this paper, we aim to simultaneously classify tweet purpose, i.e., the intention for user to publish a tweet, and position, i.e., supporting, opposing or being neutral to a given topic. By transforming this problem to a multi-label classification problem, a multi-label classification method with post-processing is proposed. Experiments on real-world data sets demonstrate the effectiveness of this method and the results outperform the individual classification methods.

Authorship identification is a process in which the author of a text is identified. Most known literary texts can easily be attributed to a certain author because they are, for example, signed. Yet sometimes we find unfinished pieces of work or a whole bunch of manuscripts with a wide variety of possible authors. In order to assess the importance of such a manuscript, it is vital to know who wrote it. In this work, we aim to develop a machine learning framework to effectively determine authorship. We formulate the task as a single-label multi-class text categorization problem and propose a supervised machine learning framework incorporating stylometric features. This task is highly interdisciplinary in that it takes advantage of machine learning, information retrieval, and natural language processing. We present an approach and a model which learns the differences in writing style between $50$ different authors and is able to predict the author of a new text with high accuracy. The accuracy is seen to increase significantly after introducing certain linguistic stylometric features along with text features.