Consistency is the theoretical property of a meta learning algorithm that ensures that, under certain assumptions, it can adapt to any task at test time. An open question is whether and how theoretical consistency translates into practice, in comparison to inconsistent algorithms. In this paper, we empirically investigate this question on a set of representative meta-RL algorithms. We find that theoretically consistent algorithms can indeed usually adapt to out-of-distribution (OOD) tasks, while inconsistent ones cannot, although they can still fail in practice for reasons like poor exploration. We further find that theoretically inconsistent algorithms can be made consistent by continuing to update all agent components on the OOD tasks, and adapt as well or better than originally consistent ones. We conclude that theoretical consistency is indeed a desirable property, and inconsistent meta-RL algorithms can easily be made consistent to enjoy the same benefits.

This paper serves to introduce the reader to the field of multi-agent reinforcement learning (MARL) and its intersection with methods from the study of causality. We highlight key challenges in MARL and discuss these in the context of how causal methods may assist in tackling them. We promote moving toward a 'causality first' perspective on MARL. Specifically, we argue that causality can offer improved safety, interpretability, and robustness, while also providing strong theoretical guarantees for emergent behaviour. We discuss potential solutions for common challenges, and use this context to motivate future research directions.

The topic of AI fairness metrics is as important to society as it is confusing. Confusing it is due to a number of reasons: terminological proliferation, abundance of formulae, and last not least the impression that everyone else seems to know what they're talking about. This text hopes to counteract some of that confusion by starting from a common-sense approach of contrasting two basic positions: On the one hand, the assumption that dataset features may be taken as reflecting the underlying concepts ML practitioners are interested in; on the other, that there inevitably is a gap between concept and measurement, a gap that may be bigger or smaller depending on what is being measured. In contrasting these fundamental views, we bring together concepts from ML, legal science, and political philosophy.

Reading: Voice-enabled reading tools can help diagnose reading challenges, including dyslexia, at an earlier stage before a child even learns to read or recognize letters or letter sounds (phonics). Then, as a child starts down their reading journey, voice-enabled reading apps can listen, prompt, correct, and encourage a child as their reading progresses, just as a helpful adult would do. Immediate and accurate feedback from the voice-enabled reading app empowers a child to progress autonomously, practice regularly, and assess their own reading ability and areas for improvement. Voice-enabled reading assessments also provide educators and parents with immediate and granular insights into where a kid is struggling and help them to support the child with more personalized and individual approaches to achieving their reading goals. Language learning: Vice-enabled tools can listen while a child reads aloud and immediately return pronunciation scores and encouraging feedback--just as a supportive adult or tutor would.

Welcome to the best Natural Language Processing course on the internet! This course is designed to be your complete online resource for learning how to use Natural Language Processing with the Python programming language. In the course we will cover everything you need to learn in order to become a world class practitioner of NLP with Python. We'll start off with the basics, learning how to open and work with text and PDF files with Python, as well as learning how to use regular expressions to search for custom patterns inside of text files. Afterwards we will begin with the basics of Natural Language Processing, utilizing the Natural Language Toolkit library for Python, as well as the state of the art Spacy library for ultra fast tokenization, parsing, entity recognition, and lemmatization of text.

AI is a broad and rapidly developing field of technology. Our goal is to make sure all young people have the skills, knowledge, and confidence to use and create AI systems. So what should AI education in schools look like? To hear a range of insights into this, we organised a panel discussion as part of our seminar series on AI and data science education, which we co-host with The Alan Turing Institute. You can also watch the recording below.

The University of Texas at Austin's "Convergent, Responsible, and Ethical AI Training Experience for Roboticists," or CREATE, program launched this year with the goal of informing trainees and graduate students on the privacy and security implications of creating robots that work alongside humans or work in homes. "Given the potentially disruptive consequences of artificial intelligence (AI)-based systems, humanity cannot afford to wait until problems arise to consider their impacts on society," an award abstract read. "AI's ethical and societal implications must be considered as systems are designed, developed, and deployed."

Imagine being able to do something without having to do it manually 100% of the time. Imagine having a virtual teaching assistant with you, as you focus on your teaching. Or, imagine having a virtual tutor on standby, if you're needing additional learning help as a student. AI offers many solutions to the current educational system. In this brief overview, we will explore 7 reasons why AI should be utilized in education.

Artificial intelligence has been used in products targeting children for several years, but legislation protecting them from the potential impacts of the technology is still in its infancy. Ahead of a global forum on AI for children, UN News spoke to two UN Children's Fund (UNICEF) experts about the need for improved policy protection. Children are already interacting with AI technologies in many different ways: they are embedded in toys, virtual assistants, video games, and adaptive learning software. Their impact on children's lives is profound, yet UNICEF found that, when it comes to AI policies and practices, children's rights are an afterthought, at best. In response, the UN children's agency has developed draft Policy Guidance on AI for Children to promote children's rights, and raise awareness of how AI systems can uphold or undermine these rights.

Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud annotations. To alleviate the annotation cost, unlabeled or weakly labeled data is still less explored in the task. In this paper, we introduce the first semi-supervised point cloud instance segmentation framework (SPIB) using both labeled and unlabelled bounding boxes as supervision. To be specific, our SPIB architecture involves a two-stage learning procedure. For stage one, a bounding box proposal generation network is trained under a semi-supervised setting with perturbation consistency regularization (SPCR). The regularization works by enforcing an invariance of the bounding box predictions over different perturbations applied to the input point clouds, to provide self-supervision for network learning. For stage two, the bounding box proposals with SPCR are grouped into some subsets, and the instance masks are mined inside each subset with a novel semantic propagation module and a property consistency graph module. Moreover, we introduce a novel occupancy ratio guided refinement module to refine the instance masks. Extensive experiments on the challenging ScanNet v2 dataset demonstrate our method can achieve competitive performance compared with the recent fully-supervised methods.