Like electricity or the internet, artificial intelligence (AI) is considered a general purpose technology with the potential to transform productivity, accelerate economic growth and improve wellbeing across the whole of society. It has started, and will continue to, drastically transform the way we work and live. At least, this is what the report'Towards Our Intelligent Future' published by New Zealand AI Forum earlier this year affirms. The report represents over nine months of collaborative work on parallel streams exploring AI adoption, policy and strategy in New Zealand and around the world. It highlights the value of AI for achieving New Zealand's wellbeing, sustainability and economic goals.

Systems powered by artificial intelligence are being developed to be more user-friendly by communicating with users in a progressively human-like conversational way. Chatbots, also known as dialogue systems, interactive conversational agents, or virtual agents are an example of such systems used in a wide variety of applications ranging from customer support in the business domain to companionship in the healthcare sector. It is becoming increasingly important to develop chatbots that can best respond to the personalized needs of their users so that they can be as helpful to the user as possible in a real human way. This paper investigates and compares three popular existing chatbots API offerings and then propose and develop a voice interactive and multilingual chatbot that can effectively respond to users mood, tone, and language using IBM Watson Assistant, Tone Analyzer, and Language Translator. The chatbot was evaluated using a use case that was targeted at responding to users needs regarding exam stress based on university students survey data generated using Google Forms. The results of measuring the chatbot effectiveness at analyzing responses regarding exam stress indicate that the chatbot responding appropriately to the user queries regarding how they are feeling about exams 76.5%. The chatbot could also be adapted for use in other application areas such as student info-centers, government kiosks, and mental health support systems.

State-of-the-art machine learning methods exhibit limited compositional generalization. At the same time, there is a lack of realistic benchmarks that comprehensively measure this ability, which makes it challenging to find and evaluate improvements. We introduce a novel method to systematically construct such benchmarks by maximizing compound divergence while guaranteeing a small atom divergence between train and test sets, and we quantitatively compare this method to other approaches for creating compositional generalization benchmarks. We present a large and realistic natural language question answering dataset that is constructed according to this method, and we use it to analyze the compositional generalization ability of three machine learning architectures. We find that they fail to generalize compositionally and that there is a surprisingly strong negative correlation between compound divergence and accuracy. We also demonstrate how our method can be used to create new compositionality benchmarks on top of the existing SCAN dataset, which confirms these findings.

We consider distributed online convex optimization problems, where the distributed system consists of various computing units connected through a time-varying communication graph. In each time step, each computing unit selects a constrained vector, experiences a loss equal to an arbitrary convex function evaluated at this vector, and may communicate to its neighbors in the graph. The objective is to minimize the system-wide loss accumulated over time. We propose a decentralized algorithm with regret and cumulative constraint violation in $\mathcal{O}(T^{\max\{c,1-c\} })$ and $\mathcal{O}(T^{1-c/2})$, respectively, for any $c\in (0,1)$, where $T$ is the time horizon. When the loss functions are strongly convex, we establish improved regret and constraint violation upper bounds in $\mathcal{O}(\log(T))$ and $\mathcal{O}(\sqrt{T\log(T)})$. These regret scalings match those obtained by state-of-the-art algorithms and fundamental limits in the corresponding centralized online optimization problem (for both convex and strongly convex loss functions). In the case of bandit feedback, the proposed algorithms achieve a regret and constraint violation in $\mathcal{O}(T^{\max\{c,1-c/3 \} })$ and $\mathcal{O}(T^{1-c/2})$ for any $c\in (0,1)$. We numerically illustrate the performance of our algorithms for the particular case of distributed online regularized linear regression problems.

In this article, we present a new data type agnostic algorithm calculating a concept lattice from heterogeneous and complex data. Our NextPriorityConcept algorithm is first introduced and proved in the binary case as an extension of Bordat's algorithm with the notion of strategies to select only some predecessors of each concept, avoiding the generation of unreasonably large lattices. The algorithm is then extended to any type of data in a generic way. It is inspired from pattern structure theory, where data are locally described by predicates independent of their types, allowing the management of heterogeneous data.

Artificial Intelligent systems are generally defined as computer systems which are to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation. In the context of Infrastructure Asset Management, there are many applications for AI which can replace or augment substantial levels of human effort in order to improve the performance of the Asset or extend its life. As many public organisations are making significant efforts to understand'best practice' asset management, often referring to ISO 550001 for guidance on the The goal of Machine Learning is to learn from data, ingesting a large volume of data a ML algorithm is predominantly focused on a certain task to maximize the performance of machine in performing that task. Artificial Intelligence, on the other hand, is primarily focused on decision making. So while ML allows a system to learn new things from data, and AI attempts to mimic human behavior in a circumstances.

As we wind up an eventful year for grantmakers in Australia and New Zealand, we think it's the perfect time to look ahead, with an examination of the strengths and weaknesses of AI-assisted grants and other ways to do better in the latest edition, Also inside: Don't forget that you can tap into our knowledge base of past newsletters, grantmaking tools and resources by visiting www.aigm.com.au. Please note, SmartyGrants readers can become an AIGM member free, for all-areas access. Plus join the AIGM for exclusives, back issues and discounts. The quarterly publication is just one of the benefits of membership of the Australian Institute of Grants Management. Learn more about Grants Management Intelligence and become a member here.

Most research on emotion analysis from text focuses on the task of emotion classification or emotion intensity regression. Fewer works address emotions as structured phenomena, which can be explained by the lack of relevant datasets and methods. We fill this gap by releasing a dataset of 5000 English news headlines annotated via crowdsourcing with their dominant emotions, emotion experiencers and textual cues, emotion causes and targets, as well as the reader's perception and emotion of the headline. We propose a multiphase annotation procedure which leads to high quality annotations on such a task via crowdsourcing. Finally, we develop a baseline for the task of automatic prediction of structures and discuss results. The corpus we release enables further research on emotion classification, emotion intensity prediction, emotion cause detection, and supports further qualitative studies.

Context-aware recommender systems (CARS) have gained increasing attention due to their ability to utilize contextual information. Compared to traditional recommender systems, CARS are, in general, able to generate more accurate recommendations. Latent factors approach accounts for a large proportion of CARS. Recently, a nonlinear Gaussian Process (GP) based factorization method was proven to outperform the state-of-the-art methods in CARS. Despite its effectiveness, GP model-based methods can suffer from over-fitting and may not be able to determine the impact of each context automatically. In order to address such shortcomings, we propose a Gaussian Process Latent V ariable Model Factorization (GPL VMF) method, where we apply an appropriate prior to the original GP model. Our work is primarily inspired by the Gaussian Process Latent V ariable Model (GPL VM), which was a nonlinear dimensionality reduction method. As a result, we improve the performance on the real datasets significantly as well as capturing the importance of each context. In addition to the general advantages, our method provides two main contributions regarding recommender system settings: (1) addressing the influence of bias by setting a nonzero mean function, and (2) utilizing real-valued contexts by fixing the latent space with real values.

In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success. The theory has been applied to various neural network structures, including CNNs, RNNs, Residual networks, and Batch normalization. Inevitably, recent work has also covered the use of dropout. The mean field theory shows that the existence of depth scales that limit the maximum depth of signal propagation and gradient backpropagation. However, the gradient backpropagation is derived under the gradient independence assumption that weights used during feed forward are drawn independently from the ones used in backpropagation. This is not how neural networks are trained in a real setting. Instead, the same weights used in a feed-forward step needs to be carried over to its corresponding backpropagation. Using this realistic condition, we perform theoretical computation on linear dropout networks and a series of experiments on dropout networks. Our empirical results show an interesting phenomenon that the length gradients can backpropagate for a single input and a pair of inputs are governed by the same depth scale. Besides, we study the relationship between variance and mean of statistical metrics of the gradient and shown an emergence of universality. Finally, we investigate the maximum trainable length for deep dropout networks through a series of experiments using MNIST and CIFAR10 and provide a more precise empirical formula that describes the trainable length than original work.