What is the real power of the adjacency matrix in a graph? In this series, we are following and studying the evolution of machine learning algorithms to deal with graphs [1,2]. Graphs can store an impressive amount of information in a very concise way [3–6], they can be employed to assess clusters of people [7–9] based on their social relationship or exploiting latent features which cannot be detected with simple linear analyses [10]. On the other side graphs are complicated mathematical structures [11,12], their input signal cannot be described on a grid and it is hard to define dominant local statistics unless we perform an average around nodes' neighbours. For these reasons, the application of powerful ML algorithms such as Convolutional Neural Network [13–15] is sometimes complicated and requires a look at the mathematical basis of what graphs are.

The graph represents a network of 4,880 Twitter users whose tweets in the requested range contained "(Artificial Intelligence) OR #AI", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Thursday, 20 January 2022 at 06:03 UTC. The requested start date was Thursday, 20 January 2022 at 01:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 7,500. The tweets in the network were tweeted over the 2-day, 0-hour, 58-minute period from Monday, 17 January 2022 at 23:25 UTC to Thursday, 20 January 2022 at 00:23 UTC.

One of the co-founders, Martin Nisser, a PhD student from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), explains the digital literacy and self-efficacy focused objectives: "Some of the women haven't had the opportunity to work with a computer for 25 years, and aren't yet accustomed to using the internet. We're working with them to build their capabilities with these modern tools in order to prepare them for life outside," says Nisser. Even for the students who became incarcerated more recently, it can be difficult to keep up with the fast pace of technological advances, since technical programs in correctional facilities are few and far-between. This scarcity of preparatory programs undoubtedly contributes to high and rising recidivism rates: More often than not, those who are released from prison eventually return. While working at TEJI, Nisser had a fortuitous meeting with his two co-founders, Marisa Gaetz (a PhD student from MIT's Department of Mathematics) and Emily Harburg (co-founder of Brave Initiatives, a nonprofit that develops coding bootcamps for young women).

What is the real power of the adjacency matrix in a graph? In this series, we are following and studying the evolution of machine learning algorithms to deal with graphs [1,2]. Graphs can store an impressive amount of information in a very concise way [3–6], they can be employed to assess clusters of people [7–9] based on their social relationship or exploiting latent features which cannot be detected with simple linear analyses [10]. On the other side graphs are complicated mathematical structures [11,12], their input signal cannot be described on a grid and it is hard to define dominant local statistics unless we perform an average around nodes' neighbours. For these reasons, the application of powerful ML algorithms such as Convolutional Neural Network [13–15] is sometimes complicated and requires a look at the mathematical basis of what graphs are.

The following is an excerpt adapted from AI 2041 by Kai-Fu Lee and Chen Qiufan. No part of this excerpt may be reproduced or reprinted without permission in writing from the publisher. Artificial intelligence can perform many tasks better than people can, at essentially zero cost. This simple fact is poised to generate tremendous economic value but also to cause unprecedented job displacement -- a wave of disruption that will hit blue- and white-collar workers alike. In the future, AI will be doing everything from underwriting our loans to building our homes, and even hiring and firing us.

To interact with humans, artificial intelligence (AI) systems must understand our social world. Within this world norms play an important role in motivating and guiding agents. However, very few computational theories for learning social norms have been proposed. There also exists a long history of debate on the distinction between what is normal (is) and what is normative (ought). Many have argued that being capable of learning both concepts and recognizing the difference is necessary for all social agents. This paper introduces and demonstrates a computational approach to learning norms from natural language text that accounts for both what is normal and what is normative. It provides a foundation for everyday people to train AI systems about social norms.

Many datasets represent a combination of several viewpoints - different ways of looking at the same data that lead to different generalizations. For example, a corpus with examples generated by different people may be mixtures of many perspectives and can be viewed with different perspectives by others. It isn't always possible to represent the viewpoints by a clean separation, in advance, of examples representing each viewpoint and train a separate model for each viewpoint. We introduce lensing, a mixed-initiative technique to (1) extract'lenses' or mappings between machine-learned representations and perspectives of human experts, and to (2) generate'lensed' models that afford multiple perspectives of the same dataset. We apply lensing for two classes of latent variable models (a) a mixed-membership model and (b) a matrix factorization model in the context of two mental health applications, and we capture and imbue the perspectives of clinical psychologists into these models. Our work shows the benefits of the machine learning practitioner formally incorporating the perspective of a knowledgeable domain expert into their models rather than estimating unlensed models themselves in isolation.

The ability to discover behaviours from past experience and transfer them to new tasks is a hallmark of intelligent agents acting sample-efficiently in the real world. Equipping embodied reinforcement learners with the same ability may be crucial for their successful deployment in robotics. While hierarchical and KL-regularized RL individually hold promise here, arguably a hybrid approach could combine their respective benefits. Key to these fields is the use of information asymmetry to bias which skills are learnt. While asymmetric choice has a large influence on transferability, prior works have explored a narrow range of asymmetries, primarily motivated by intuition. In this paper, we theoretically and empirically show the crucial trade-off, controlled by information asymmetry, between the expressivity and transferability of skills across sequential tasks. Given this insight, we provide a principled approach towards choosing asymmetry and apply our approach to a complex, robotic block stacking domain, unsolvable by baselines, demonstrating the effectiveness of hierarchical KL-regularized RL, coupled with correct asymmetric choice, for sample-efficient transfer learning.

We present a two-step hybrid reinforcement learning (RL) policy that is designed to generate interpretable and robust hierarchical policies on the RL problem with graph-based input. Unlike prior deep reinforcement learning policies parameterized by an end-to-end black-box graph neural network, our approach disentangles the decision-making process into two steps. The first step is a simplified classification problem that maps the graph input to an action group where all actions share a similar semantic meaning. The second step implements a sophisticated rule-miner that conducts explicit one-hop reasoning over the graph and identifies decisive edges in the graph input without the necessity of heavy domain knowledge. This two-step hybrid policy presents human-friendly interpretations and achieves better performance in terms of generalization and robustness. Extensive experimental studies on four levels of complex text-based games have demonstrated the superiority of the proposed method compared to the state-of-the-art.

Figural analogy problems have long been a widely used format in human intelligence tests. In the past four decades, more and more research has investigated automatic item generation for figural analogy problems, i.e., algorithmic approaches for systematically and automatically creating such problems. In cognitive science and psychometrics, this research can deepen our understandings of human analogical ability and psychometric properties of figural analogies. With the recent development of data-driven AI models for reasoning about figural analogies, the territory of automatic item generation of figural analogies has further expanded. This expansion brings new challenges as well as opportunities, which demand reflection on previous item generation research and planning future studies. This paper reviews the important works of automatic item generation of figural analogies for both human intelligence tests and data-driven AI models. From an interdisciplinary perspective, the principles and technical details of these works are analyzed and compared, and desiderata for future research are suggested.