Collaborative learning has successfully applied knowledge transfer to guiding a pool of small student networks towards robust local minima. However, previous approaches typically struggle with drastically aggravated student homogenization and rapidly growing computational complexity when the number of students rises. In this paper, we propose Collaborative Group Learning, an efficient framework that aims to maximize student population without sacrificing generalization performance and computational efficiency. First, each student is established by randomly routing on a modular neural network, which is not only parameter-efficient but also facilitates flexible knowledge communication between students due to random levels of representation sharing and branching. Second, to resist homogenization and further reduce the computational cost, students first compose diverse feature sets by exploiting the inductive bias from sub-sets of training data, and then aggregate and distill supplementary knowledge by choosing a random sub-group of students at each time step. Empirical evaluations on both image and text tasks indicate that our method significantly outperforms various state-of-the-art collaborative approaches whilst enhancing computational efficiency.

How to Engage Your Audience and Save Them From Zoom Fatigue by Amelia Ma Zoom fatigue is a term that has quickly emerged into our consciousness during the pandemic crisis. This post by Amelia Ma looks at various techniques you can use to engage people while also being sensitive to the reality of Zoom fatigue.

Paul Grist, Head of Education, International, Amazon Web Services (AWS) Future of Apprenticeships This week (14-18 Sept) is Artificial Intelligence (#AI) and Machine Learning (#ML) Week @AWS_Edu, Head of Education, Paul Grist explains how Machine Learning can help teachers and improve student outcomes. The COVID-19 crisis has forced millions of teachers around the world to rapidly learn how to use technology to effectively support student learning and assessment, stay connected with their students, experiment with teaching models, and reduce the workload so they can focus on teaching. There are many promising solutions that are helping teachers become more effective, including new technologies such as machine learning (ML), artificial intelligence (AI) and optimised workflows. For example, Revisely is an education company that helps teachers give better feedback on students' writing assignments, such as essays and papers. It saves teachers time by offering built-in comment sets and doing a plagiarism check on student work, among other features.

Strategic recommendations (SR) refer to the problem where an intelligent agent observes the sequential behaviors and activities of users and decides when and how to interact with them to optimize some long-term objectives, both for the user and the business. These systems are in their infancy in the industry and in need of practical solutions to some fundamental research challenges. At Adobe research, we have been implementing such systems for various use-cases, including points of interest recommendations, tutorial recommendations, next step guidance in multi-media editing software, and ad recommendation for optimizing lifetime value. There are many research challenges when building these systems, such as modeling the sequential behavior of users, deciding when to intervene and offer recommendations without annoying the user, evaluating policies offline with high confidence, safe deployment, non-stationarity, building systems from passive data that do not contain past recommendations, resource constraint optimization in multi-user systems, scaling to large and dynamic actions spaces, and handling and incorporating human cognitive biases. In this paper we cover various use-cases and research challenges we solved to make these systems practical.

Although NumNet achieves superior performance than Numerical reasoning over texts, such as addition, other numerically-aware models (Hu et al., 2019a; Andor subtraction, sorting and counting, is a et al., 2019; Geva et al., 2020; Chen et al., 2020), we challenging machine reading comprehension argue that NumNet is insufficient for sophisticated numerical task, since it requires both natural language understanding reasoning, since it lacks two critical ingredients and arithmetic computation. To for numerical reasoning: address this challenge, we propose a heterogeneous 1. Number Type and Entity Mention. The number graph representation for the context of comparison graph in NumNet is not able to identify the passage and question needed for such reasoning, different number types, and lacks the information of and design a question directed graph entities mentioned in the document that connect the attention network to drive multi-step numerical number nodes.

In our previous work we have shown how Bayesian networks can be used for adaptive testing of student skills. Later, we have taken the advantage of monotonicity restrictions in order to learn models fitting data better. This article provides a synergy between these two phases as it evaluates Bayesian network models used for computerized adaptive testing and learned with a recently proposed monotonicity gradient algorithm. This learning method is compared with another monotone method, the isotonic regression EM algorithm. The quality of methods is empirically evaluated on a large data set of the Czech National Mathematics Exam. Besides advantages of adaptive testing approach we observed also advantageous behavior of monotonic methods, especially for small learning data set sizes. Another novelty of this work is the use of the reliability interval of the score distribution, which is used to predict student's final score and grade. In the experiments we have clearly shown we can shorten the test while keeping its reliability. We have also shown that the monotonicity increases the prediction quality with limited training data sets. The monotone model learned by the gradient method has a lower question prediction quality than unrestricted models but it is better in the main target of this application, which is the student score prediction. It is an important observation that a mere optimization of the model likelihood or the prediction accuracy do not necessarily lead to a model that describes best the student.

We proposed a novel AI framework to conduct real-time multi-speaker diarization and recognition without prior registration and pretraining in a fully online learning setting. Our contributions are two-fold. First, we proposed a new benchmark to evaluate the rarely studied fully online speaker diarization problem. We built upon existing datasets of real world utterances to automatically curate MiniVox, an experimental environment which generates infinite configurations of continuous multi-speaker speech stream. Secondly, we considered the practical problem of online learning with episodically revealed rewards and introduced a solution based on semi-supervised and self-supervised learning methods. Lastly, we provided a workable web-based recognition system which interactively handles the cold start problem of new user's addition by transferring representations of old arms to new ones with an extendable contextual bandit. We demonstrated that our proposed method obtained robust performance in the online MiniVox framework.

Recent work has shown that large text-based neural language models, trained with conventional supervised learning objectives, acquire a surprising propensity for few- and one-shot learning. Here, we show that an embodied agent situated in a simulated 3D world, and endowed with a novel dual-coding external memory, can exhibit similar one-shot word learning when trained with conventional reinforcement learning algorithms. After a single introduction to a novel object via continuous visual perception and a language prompt ("This is a dax"), the agent can re-identify the object and manipulate it as instructed ("Put the dax on the bed"). In doing so, it seamlessly integrates short-term, within-episode knowledge of the appropriate referent for the word "dax" with long-term lexical and motor knowledge acquired across episodes (i.e. "bed" and "putting"). We find that, under certain training conditions and with a particular memory writing mechanism, the agent's one-shot word-object binding generalizes to novel exemplars within the same ShapeNet category, and is effective in settings with unfamiliar numbers of objects. We further show how dual-coding memory can be exploited as a signal for intrinsic motivation, stimulating the agent to seek names for objects that may be useful for later executing instructions. Together, the results demonstrate that deep neural networks can exploit meta-learning, episodic memory and an explicitly multi-modal environment to account for 'fast-mapping', a fundamental pillar of human cognitive development and a potentially transformative capacity for agents that interact with human users.

We propose a generative framework for joint sequence labeling and sentence-level classification. Our model performs multiple sequence labeling tasks at once using a single, shared natural language output space. Unlike prior discriminative methods, our model naturally incorporates label semantics and shares knowledge across tasks. Our framework is general purpose, performing well on few-shot, low-resource, and high-resource tasks. We demonstrate these advantages on popular named entity recognition, slot labeling, and intent classification benchmarks. We set a new state-of-the-art for few-shot slot labeling, improving substantially upon the previous 5-shot ($75.0\% \rightarrow 90.9\%$) and 1-shot ($70.4\% \rightarrow 81.0\%$) state-of-the-art results. Furthermore, our model generates large improvements ($46.27\% \rightarrow 63.83\%$) in low-resource slot labeling over a BERT baseline by incorporating label semantics. We also maintain competitive results on high-resource tasks, performing within two points of the state-of-the-art on all tasks and setting a new state-of-the-art on the SNIPS dataset.

This paper proposes a novel fixed inducing points online Bayesian calibration (FIPO-BC) algorithm to efficiently learn the model parameters using a benchmark database. The standard Bayesian calibration (STD-BC) algorithm provides a statistical method to calibrate the parameters of computationally expensive models. However, the STD-BC algorithm scales very badly with the number of data points and lacks online learning capability. The proposed FIPO-BC algorithm greatly improves the computational efficiency and enables the online calibration by executing the calibration on a set of predefined inducing points. To demonstrate the procedure of the FIPO-BC algorithm, two tests are performed, finding the optimal value and exploring the posterior distribution of 1) the parameter in a simple function, and 2) the high-wave number damping factor in a scale-resolving turbulence model (SAS-SST). The results (such as the calibrated model parameter and its posterior distribution) of FIPO-BC with different inducing points are compared to those of STD-BC. It is found that FIPO-BC and STD-BC can provide very similar results, once the predefined set of inducing point in FIPO-BC is sufficiently fine. But, the FIPO-BC algorithm is at least ten times faster than the STD-BC algorithm. Meanwhile, the online feature of the FIPO-BC allows continuous updating of the calibration outputs and potentially reduces the workload on generating the database.