Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural way. When teaching tasks that involve sequences of different skills, with varying order and number of these skills, it is desirable to only demonstrate full task executions instead of all individual skills. For this purpose, we propose a novel approach that simultaneously learns to segment trajectories into reoccurring patterns and the skills to reconstruct these patterns from unlabelled demonstrations without further supervision. Moreover, the approach learns a skill conditioning that can be used to understand possible sequences of skills, a practical mechanism to be used in, for example, human-robot-interactions for a more intelligent and adaptive robot behaviour. The Bayesian and variational inference based approach is evaluated on synthetic and real human demonstrations with varying complexities and dimensionality, showing the successful learning of segmentations and skill libraries from unlabelled data.

Conventional Machine Reading Comprehension (MRC) has been well-addressed by pattern matching, but the ability of commonsense reasoning remains a gap between humans and machines. Previous methods tackle this problem by enriching word representations via pre-trained Knowledge Graph Embeddings (KGE). However, they make limited use of a large number of connections between nodes in Knowledge Graphs (KG), which could be pivotal cues to build the commonsense reasoning chains. In this paper, we propose a Plug-and-play module to IncorporatE Connection information for commonsEnse Reasoning (PIECER). Beyond enriching word representations with knowledge embeddings, PIECER constructs a joint query-passage graph to explicitly guide commonsense reasoning by the knowledge-oriented connections between words. Further, PIECER has high generalizability since it can be plugged into suitable positions in any MRC model. Experimental results on ReCoRD, a large-scale public MRC dataset requiring commonsense reasoning, show that PIECER introduces stable performance improvements for four representative base MRC models, especially in low-resource settings.

The AXELOS Best Practice Podcast – the essential (audio) guide to help you and your organizations create better outcomes while promoting best practice within IT service management (ITSM) and Programme and Project Management (PPM). Our two regular hosts, AXELOS’ ITSM Ambassador Akshay Anand and PPM Ambassador Allan Thomson, will speak to guests from a variety of backgrounds. They’ll share their insight, knowledge and opinion based on their own experiences and professional expertise. We’ll share a new episode with you twice a month. So, tune in and enjoy our podcast.

Science and technology curricula in UK schools are'not fit for purpose' and need to be updated to help pupils'change the world for the better', teachers have warned. Polls taken amid COVID-19 on behalf of the Amazon Longitude Explorer Prize found 47 per cent of teachers think the technology curriculum, specifically, is out of date. More than half of teachers said they had not the support to ensure lessons kept pace with advances and 59 per cent said resource shortages were limiting lesson plans. And 59 per cent said the STEM (Science, Technology, Engineering and Mathematics) curricula constrain their ability to help students reach their potential. The findings also flagged issues that have arisen specifically as a consequence of the COVID-19 pandemic -- including the impact such has had on practical teaching.

Learning foundational IT, data science or programming skills is necessary if you want to work in a technical field, but using them outside of these environments can benefit your productivity and efficiency in the workplace. Not to mention, employers value these talents, so acquiring one of these disciplines can help your resume stand out or even get your name to the top of the list the next time it's promotion season. If that sounds appealing to you, the 2021 Complete Computer Science Training Bundle will be a worthwhile investment in your professional development at $40. This bundle features 212 hours of curated classes on Python, Tensorflow, data analysis, applied probability and more. The bundle begins with "Python Data Science," a practical, hands-on course that will teach you exactly how to use this language in data science and machine learning with data analysis, visualization and practical applications of your findings.

The original version of this article appeared in Toward Data Science. When I started teaching data science and artificial intelligence in Duke University's Pratt School of Engineering, I was frustrated by how little insight I actually felt I had into how effective my teaching was, until the end-of-semester final exam grades and student assessments came in. Being new to teaching, I spent time reading up on pedagogical best practices and how methods like mastery learning and one-on-one personalized guidance could drastically improve student outcomes. Yet even with my relatively small class sizes I did not feel I had enough insight into each individual student's learning to provide useful personalized guidance to them. In the middle of the semester, if you had asked me to tell you exactly what a specific student had mastered from the class to date and where he or she was struggling, I would not have been able to give you a very good answer.

Though pre-trained language models such as Bert and XLNet, have rapidly advanced the state-of-the-art on many NLP tasks, they implicit semantics only relying on surface information between words in corpus. Intuitively, background knowledge influences the efficacy of understanding. Inspired by this common sense, we focus on improving model pretraining by leveraging explicit knowledge. Different from recent research that optimize pretraining model by knowledge masking strategies, we propose a simple but general method to combine explicit knowledge with pretraining. To be specific, we first match knowledge facts from knowledge graph (KG) and then add a knowledge injunction layer to transformer directly without changing its architecture. The present study seeks to find the direct impact of explicit knowledge on transformer per-training. We conduct experiments on various datasets for different downstream tasks. The experimental results show that solely by adding external knowledge to transformer can improve the learning performance on many NLP tasks.

General AI system solves a wide range of tasks with high performance in an automated fashion. The best general AI algorithm designed by one individual is different from that devised by another. The best performance records achieved by different users are also different. An inevitable component of general AI is tacit knowledge that depends upon user-specific comprehension of task information and individual model design preferences that are related to user technical experiences. Tacit knowledge affects model performance but cannot be automatically optimized in general AI algorithms. In this paper, we propose User-Oriented Smart General AI System under Causal Inference, abbreviated as UOGASuCI, where UOGAS represents User-Oriented General AI System and uCI means under the framework of causal inference. User characteristics that have a significant influence upon tacit knowledge can be extracted from observed model training experiences of many users in external memory modules. Under the framework of causal inference, we manage to identify the optimal value of user characteristics that are connected with the best model performance designed by users. We make suggestions to users about how different user characteristics can improve the best model performance achieved by users. By recommending updating user characteristics associated with individualized tacit knowledge comprehension and technical preferences, UOGAS helps users design models with better performance.

We introduce the problem of robust subgroup discovery, i.e., finding a set of interpretable descriptions of subsets that 1) stand out with respect to one or more target attributes, 2) are statistically robust, and 3) non-redundant. Many attempts have been made to mine either locally robust subgroups or to tackle the pattern explosion, but we are the first to address both challenges at the same time from a global perspective. First, we formulate a broad model class of subgroup lists, i.e., ordered sets of subgroups, for univariate and multivariate targets that can consist of nominal or numeric variables. This novel model class allows us to formalize the problem of optimal robust subgroup discovery using the Minimum Description Length (MDL) principle, where we resort to optimal Normalized Maximum Likelihood and Bayesian encodings for nominal and numeric targets, respectively. Notably, we show that our problem definition is equal to mining the top-1 subgroup with an information-theoretic quality measure plus a penalty for complexity. Second, as finding optimal subgroup lists is NP-hard, we propose RSD, a greedy heuristic that finds good subgroup lists and guarantees that the most significant subgroup found according to the MDL criterion is added in each iteration, which is shown to be equivalent to a Bayesian one-sample proportions, multinomial, or t-test between the subgroup and dataset marginal target distributions plus a multiple hypothesis testing penalty. We empirically show on 54 datasets that RSD outperforms previous subgroup set discovery methods in terms of quality and subgroup list size.

Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this and other video understanding tasks, supervised approaches have achieved encouraging performance but require a high volume of detailed frame-level annotations. We present a fully automatic and unsupervised approach for segmenting actions in a video that does not require any training. Our proposal is an effective temporally-weighted hierarchical clustering algorithm that can group semantically consistent frames of the video. Our main finding is that representing a video with a 1-nearest neighbor graph by taking into account the time progression is sufficient to form semantically and temporally consistent clusters of frames where each cluster may represent some action in the video. Additionally, we establish strong unsupervised baselines for action segmentation and show significant performance improvements over published unsupervised methods on five challenging action segmentation datasets. Our approach also outperforms weakly-supervised methods by large margins on 4 of these datasets. Interestingly, we also achieve better results than many fully-supervised methods that have reported results on these datasets. Our code is available at https://github.com/ssarfraz/FINCH-Clustering/tree/master/TW-FINCH