This volume contains revised versions of the papers selected for the second volume of the Online Handbook of Argumentation for AI (OHAAI). Previously, formal theories of argument and argument interaction have been proposed and studied, and this has led to the more recent study of computational models of argument. Argumentation, as a field within artificial intelligence (AI), is highly relevant for researchers interested in symbolic representations of knowledge and defeasible reasoning. The purpose of this handbook is to provide an open access and curated anthology for the argumentation research community. OHAAI is designed to serve as a research hub to keep track of the latest and upcoming PhD-driven research on the theory and application of argumentation in all areas related to AI.

A British-built solar powered drone with a 115ft wingspan that can stay in the air for over a year will be an alternative to low Earth orbit satellites, its developers claim. PHASA-35 is a cutting edge drone being developed by BAE systems at their facility in Warton, Lancashire that can fly about at 70,000ft above the surface for 20 months. It harnesses power from the Sun to stay airborne, charging a bank of small batteries during the day to keep it flying overnight, allowing for longer operations. The 150kg drone is able to carry a payload of up to 15kg including cameras, sensors and communications equipment to allow troops to talk to each other or provide internet access to rural locations during a natural disaster or emergency. BAE systems say it will be available by the middle of the decade and provide a'persistent and affordable alternative to satellite technology.'

Hey there Noonies! Hope the afternoon is going great with lots of code and coffee. Even I was just sitting by the window enjoying rain when suddenly the sky turned dark and I wanted to switch on the light to read my book better, but the switch is on the other side of the room! So, I just said, Hey Alexa, switch on the lights, and voila! After a while I switched on my TV and there it was, Gracie, helping out the covid patients and our front line superheroes amidst the pandemic. From a light switch to a pandemic, seems like artificial intelligence is slowly winning the world. Well, if you wanna join the race, here you go with the top stories on Artificial Intelligence on Hacker Noon.

Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency regularization, pseudo-labeling has shown promising performance in various domains, for example in computer vision. To account for the hypothetical nature of the pseudo-labels, these are commonly provided in the form of probability distributions. Still, one may argue that even a probability distribution represents an excessive level of informedness, as it suggests that the learner precisely knows the ground-truth conditional probabilities. In our approach, we therefore allow the learner to label instances in the form of credal sets, that is, sets of (candidate) probability distributions. Thanks to this increased expressiveness, the learner is able to represent uncertainty and a lack of knowledge in a more flexible and more faithful manner. To learn from weakly labeled data of that kind, we leverage methods that have recently been proposed in the realm of so-called superset learning. In an exhaustive empirical evaluation, we compare our methodology to state-of-the-art self-supervision approaches, showing competitive to superior performance especially in low-label scenarios incorporating a high degree of uncertainty.

We build on the In this paper we present our submission which tries to address unsupervised representations of speech proposed by the organizers all four tasks. We extend the baseline solution in several as a baseline, derived from CPC and clustered with the k-directions: we refine the intermediate representations, extracted means algorithm. We demonstrate that simple methods of refining with CPC, to directly improve the ABX scores. We show that those representations can narrow the gap, or even improve such representations can be used to perform simple fuzzy lookups upon the solutions which use a high computational budget. The in a large dataset, and even extract some common patterns results lead to the conclusion that the CPC-derived representations that serve as pseudo-words. Our approach to the semantic word are still too noisy for training language models, but stable similarity task is also based on pseudo-words.

The article proposes a new type of AI system that does not give solutions directly but rather points toward it, friendly prompting the user with questions and adjusting messages. Models of AI - human collaboration can be deduced from the classic literary example of interaction between Mr. Holmes and Dr. Watson from the stories by Conan Doyle, where the highly qualified expert Mr. Holmes, answers questions posed by Dr. Watson. Here Mr. Holmes, with his rule-based calculations, logic and memory management apparently plays the role of an AI system and Dr. Watson is the user. Looking into the same Holmes-Watson interaction, we find and promote another model in which the AI behaves like Dr. Watson, who, by asking questions and acting in a particular way, helps Holmes (the AI user) to make the right decisions. We call the systems based on this principle "Dr.Watson-type systems". The article describes the properties of such systems and introduces two particular - Patient Management System for intensive care physicians and Data Error Prevention System.

We study fast algorithms for statistical regression problems under the strong contamination model, where the goal is to approximately optimize a generalized linear model (GLM) given adversarially corrupted samples. Prior works in this line of research were based on the robust gradient descent framework of Prasad et. al., a first-order method using biased gradient queries, or the Sever framework of Diakonikolas et. al., an iterative outlier-removal method calling a stationary point finder. We present nearly-linear time algorithms for robust regression problems with improved runtime or estimation guarantees compared to the state-of-the-art. For the general case of smooth GLMs (e.g. logistic regression), we show that the robust gradient descent framework of Prasad et. al. can be accelerated, and show our algorithm extends to optimizing the Moreau envelopes of Lipschitz GLMs (e.g. support vector machines), answering several open questions in the literature. For the well-studied case of robust linear regression, we present an alternative approach obtaining improved estimation rates over prior nearly-linear time algorithms. Interestingly, our method starts with an identifiability proof introduced in the context of the sum-of-squares algorithm of Bakshi and Prasad, which achieved optimal error rates while requiring large polynomial runtime and sample complexity. We reinterpret their proof within the Sever framework and obtain a dramatically faster and more sample-efficient algorithm under fewer distributional assumptions.

Inspired by evidence that pretrained language models (LMs) encode commonsense knowledge, recent work has applied LMs to automatically populate commonsense knowledge graphs (CKGs). However, there is a lack of understanding on their generalization to multiple CKGs, unseen relations, and novel entities. This paper analyzes the ability of LMs to perform generalizable commonsense inference, in terms of knowledge capacity, transferability, and induction. Our experiments with these three aspects show that: (1) LMs can adapt to different schemas defined by multiple CKGs but fail to reuse the knowledge to generalize to new relations. (2) Adapted LMs generalize well to unseen subjects, but less so on novel objects. Future work should investigate how to improve the transferability and induction of commonsense mining from LMs.

Over the past two decades, recommender systems have attracted a lot of interest due to the explosion in the amount of data in online applications. A particular attention has been paid to collaborative filtering, which is the most widely used in applications that involve information recommendations. Collaborative filtering (CF) uses the known preference of a group of users to make predictions and recommendations about the unknown preferences of other users (recommendations are made based on the past behavior of users). First introduced in the 1990s, a wide variety of increasingly successful models have been proposed. Due to the success of machine learning techniques in many areas, there has been a growing emphasis on the application of such algorithms in recommendation systems. In this article, we present an overview of the CF approaches for recommender systems, their two main categories, and their evaluation metrics. We focus on the application of classical Machine Learning algorithms to CF recommender systems by presenting their evolution from their first use-cases to advanced Machine Learning models. We attempt to provide a comprehensive and comparative overview of CF systems (with python implementations) that can serve as a guideline for research and practice in this area.

Human interactions with the physical environment are often mediated through information services, and sometimes depend on them. These human interactions with their environment relate to a range of scales,28 in the scenario here from the "west of the city" to the "back of the store," or beyond the scenario to "the cat is under the sofa." These interactions go far beyond references to places that are recorded in geographic gazetteers,37 both in scale (the place where the cat is) and conceptualization (the place that forms the west of the city29), or that fit to the classical coordinate-based representations of digital maps. And yet, these kinds of services have to use such digital representations of environments, such as digital maps, building information models, knowledge bases, or just text/documents. Also, their abilities to interact are limited to either fusing with the environment,44 or using media such as maps, photos, augmented reality, or voice. These interactions also happen in a vast range of real-world contexts, or in situ, in which conversation partners typically adapt their conversational strategies to their interlocutor, based on mutual information, activities, and the shared situation.2 Verbal information sharing and conversations about places may also be more suitable when visual communication through maps or imagery is inaccessible, distracting, or irrelevant, such as when navigating in a familiar shopping mall.