Think chatbots, intelligent virtual assistants, and digital employees. These and other related technologies enable computers to engage in dialogue with people in natural ways using conversational artificial intelligence (CAI). For banks, CAI makes it possible to respond to customers' questions more quickly, cost-effectively, and consistently than they could with a traditional workforce. Many banks have embarked on the CAI journey by launching chatbots. For example, HSBC and Bank of America have introduced digital financial assistants Amy and Erica, respectively.

Did you know 83% of business owners, executives and managers consider Artificial Intelligence (AI) a top priority for their business strategy, while 37% of organisations claim to have already implemented AI technology in some form? With every new AI technology or machine learning breakthrough, business leaders are increasingly recognising the strength of AI. Customer service departments are starting to choose AI virtual assistants that provide real-time support, while other companies are using AI to predict consumer behaviour to tailor offers and marketing materials more effectively. It's no secret that marketing is essential in helping businesses create and establish long-lasting relationships with their audiences, and marketing for technology businesses is no different. Technology is ever-changing, so it's crucial that technical companies adapt and focus on the long-term to keep up with the evolving market.

It is an hour past midnight and you are still wide awake. After scrolling through various social media feeds, you decide you need to talk to someone. The question is, who is actually available for a chat right now? Then you remember, your one-night owl buddy who is always up for a conversation the moment you say, "hey, are you awake?" Lo and behold, your buddy is awake, and even though he is busy eating a late night snack of pizzas, he is ready for some banter. You chat for a bit about things like favorite episodes of Stranger Things, how poorly rested he is and that it is getting late, and that you have work tomorrow morning so you say "good night" and fall back to bed.

Learning from non-stationary data remains a great challenge for machine learning. Continual learning addresses this problem in scenarios where the learning agent faces a stream of changing tasks. In these scenarios, the agent is expected to retain its highest performance on previous tasks without revisiting them while adapting well to the new tasks. Two new recent continual-learning scenarios have been proposed. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting when trained on a sequence of tasks. In continual-meta learning, the goal is faster remembering, i.e., focusing on how quickly the agent recovers performance rather than measuring the agent's performance without any adaptation. Both scenarios have the potential to propel the field forward. Yet in their original formulations, they each have limitations. As a remedy, we propose a more general scenario where an agent must quickly solve (new) out-of-distribution tasks, while also requiring fast remembering. We show that current continual learning, meta learning, meta-continual learning, and continual-meta learning techniques fail in this new scenario. Accordingly, we propose a strong baseline: Continual-MAML, an online extension of the popular MAML algorithm. In our empirical experiments, we show that our method is better suited to the new scenario than the methodologies mentioned above, as well as standard continual learning and meta learning approaches.

Increasingly complex and autonomous robots are being deployed in real-world environments with far-reaching consequences. High-stakes scenarios, such as emergency response or offshore energy platform and nuclear inspections, require robot operators to have clear mental models of what the robots can and can't do. However, operators are often not the original designers of the robots and thus, they do not necessarily have such clear mental models, especially if they are novice users. This lack of mental model clarity can slow adoption and can negatively impact human-machine teaming. We propose that interaction with a conversational assistant, who acts as a mediator, can help the user with understanding the functionality of remote robots and increase transparency through natural language explanations, as well as facilitate the evaluation of operators' mental models.

Points of interest (POI) recommendation has been drawn much attention recently due to the increasing popularity of location-based networks, e.g., Foursquare and Yelp. Among the existing approaches to POI recommendation, Matrix Factorization (MF) based techniques have proven to be effective. However, existing MF approaches suffer from two major problems: (1) Expensive computations and storages due to the centralized model training mechanism: the centralized learners have to maintain the whole user-item rating matrix, and potentially huge low rank matrices. (2) Privacy issues: the users' preferences are at risk of leaking to malicious attackers via the centralized learner. To solve these, we present a Decentralized MF (DMF) framework for POI recommendation. Specifically, instead of maintaining all the low rank matrices and sensitive rating data for training, we propose a random walk based decentralized training technique to train MF models on each user's end, e.g., cell phone and Pad. By doing so, the ratings of each user are still kept on one's own hand, and moreover, decentralized learning can be taken as distributed learning with multi-learners (users), and thus alleviates the computation and storage issue. Experimental results on two real-world datasets demonstrate that, comparing with the classic and state-of-the-art latent factor models, DMF significantly improvements the recommendation performance in terms of precision and recall.

The growing availability of user-specific data has welcomed the exciting era of personalized recommendation, a paradigm that uncovers the heterogeneity across individuals and provides tailored service decisions that lead to improved outcomes. Such heterogeneity is ubiquitous across a variety of application domains (including online advertising, medical treatment assignment, product/news recommendation ([29], [9],[11],[7],[42])) and manifests itself as different individuals responding differently to the recommended items. Rising to this opportunity, contextual bandits ([8, 39, 22, 1, 3]) have emerged to be the predominant mathematical formalism that provides an elegant and powerful formulation: its three core components, the features (representing individual characteristics), the actions (representing the recommendation), and the rewards (representing the observed feedback), capture the salient aspects of the problem and provide fertile ground for developing algorithms that balance exploring and exploiting users' heterogeneity. As such, the last decade has witnessed extensive research efforts in developing effective and efficient contextual bandits algorithms. In particular, two types of algorithms-upper confidence bounds (UCB) based algorithms ([29, 20, 15, 26, 30]) and Thompson sampling (TS) based algorithms ([4, 5, 40, 41, 2])-stand out from this flourishing and fruitful line of work: their theoretical guarantees have been analyzed in many settings, often yielding (near-)optimal regret bounds; their empirical performance have been thoroughly validated, often providing insights into their practical efficacy (including the consensus that TS based algorithms, although sometimes suffering from intensive computation for posterior updates, are generally more effective than their UCB counterparts, whose performance can be sensitive to hyper-parameter tuning). To a large extent, these two family of algorithms have been widely deployed in many modern recommendation engines.

Understanding the fundamentals of human reasoning is central to the development of any system built to closely interact with humans. Cognitive science pursues the goal of modeling human-like intelligence from a theory-driven perspective with a strong focus on explainability. Syllogistic reasoning as one of the core domains of human reasoning research has seen a surge of computational models being developed over the last years. However, recent analyses of models' predictive performances revealed a stagnation in improvement. We believe that most of the problems encountered in cognitive science are not due to the specific models that have been developed but can be traced back to the peculiarities of behavioral data instead. Therefore, we investigate potential data-related reasons for the problems in human reasoning research by comparing model performances on human and artificially generated datasets. In particular, we apply collaborative filtering recommenders to investigate the adversarial effects of inconsistencies and noise in data and illustrate the potential for data-driven methods in a field of research predominantly concerned with gaining high-level theoretical insight into a domain. Our work (i) provides insight into the levels of noise to be expected from human responses in reasoning data, (ii) uncovers evidence for an upper-bound of performance that is close to being reached urging for an extension of the modeling task, and (iii) introduces the tools and presents initial results to pioneer a new paradigm for investigating and modeling reasoning focusing on predicting responses for individual human reasoners.

The Gaussian process bandit is a problem in which we want to find a maximizer of a black-box function with the minimum number of function evaluations. If the black-box function varies with time, then time-varying Bayesian optimization is a promising framework. However, a drawback with current methods is in the assumption that the evaluation time for every observation is constant, which can be unrealistic for many practical applications, e.g., recommender systems and environmental monitoring. As a result, the performance of current methods can be degraded when this assumption is violated. To cope with this problem, we propose a novel time-varying Bayesian optimization algorithm that can effectively handle the non-constant evaluation time. Furthermore, we theoretically establish a regret bound of our algorithm. Our bound elucidates that a pattern of the evaluation time sequence can hugely affect the difficulty of the problem. We also provide experimental results to validate the practical effectiveness of the proposed method.

Recommendation systems drive engagement on many of the most popular online platforms. As the growth in the volume of data available to power these systems accelerates rapidly, data scientists are increasingly turning from more traditional machine learning methods to highly expressive deep learning models to improve the quality of their recommendations. Google's Wide & Deep architecture has emerged as a popular choice of model for these problems, both for its robustness to signal sparsity, as well as its user-friendly implementation in TensorFlow via the DNNLinearCombinedClassifier API. While the cost and latency induced by the complexity of these deep learning models can be initially very expensive for inference applications, we'll show that an accelerated, mixed-precision implementation of them optimized for NVIDIA GPUs can drastically reduce latency while obtaining impressive improvements in cost/inference. This paves the way for fast, low-cost, scalable recommendation systems well suited to both online and offline deployment and implemented using simple and familiar TensorFlow APIs. In this blog, we describe a highly optimized, GPU-accelerated inference implementation of the Wide & Deep architecture based on TensorFlow's DNNLinearCombinedClassifier API. The solution we propose allows for easy conversion from a trained TensorFlow Wide & Deep model to a mixed precision inference deployment. We also present performance results of this solution based on a representative dataset and show that GPU inference for Wide & Deep models can produce up to a 13x reduction in latency or a 11x throughput improvement in online and offline scenarios respectively. While we all likely have an intuitive understanding of what it is to make a recommendation, the question of how a machine learning model might make one is much less obvious. After all, there is something very prescriptive about the concept of a recommendation: "you should watch movie A", "you should eat the tagliatelle at restaurant B".