Sequential Task Research Articles

Assessing Theory of Mind in Children: A Tablet-Based Adaptation of a Classic Picture Sequencing Task.

Correctly assessing children's theory of mind (TOM) is essential to clinical practice. Yet, most tasks heavily rely on language, which is an obstacle for several populations. Langdon and Coltheart's (Cognition 71(1):43-71, 1999) Picture Sequencing Task (PST), developed for research purposes, avoids this limitation through a minimally-verbal procedure. We thus developed a tablet adaptation of this task for individual application, engaging children's motivation and allowing response times collection. To assess this tablet-PST, we first tested a large sample of neurotypical children (6-11 years-old, N = 248), whose results confirmed the task's structural and content validity, and permitted the construction of three standardized clinical indices. In a second experiment, we applied those to previously diagnosed autistic children (N = 23), who were expected to show atypical TOM performance. Children's outcomes were consistent with what was hypothesized and confirmed the task's external validity and moderate clinical sensitivity. The tablet-PST thus appears as a suitable tool, providing detailed profiles to inform clinical decisions.

Automated workflow generation supporting the value stream design of reconfigurable robot assembly cells

The paper addresses the automated generation of value stream optimized assembly workflows for reconfigurable robot cells. The focus is on the generation of asynchronous concurrent action workflows from assembly task descriptions. The main motivation is to enable automated search for optimized solutions within the enormous design spaces of these systems which results from their structural and procedural configurability. The proposed approach conducts task assignment, task sequencing and logical task planning (AI Planning) for multiple agents. The approach combines existing methods from the distinct research fields of robot task sequencing and discrete task planning. The contribution of the research is twofold. Firstly, the paper proposes a generic domain meta model enabling automated workflow generation for multi-agent assembly tasks. Secondly, a workflow generation approach based on artificial intelligence planning combined with the game-theoretic concept of extensive form games is presented. The approach iteratively generates a cooperative strategy for acting agents which is subsequently optimized in terms of individual strategies. The obtained logical action plans are further transformed into parametric concurrent action schedules to support downstream design activities. Both the meta model and the workflow generation approach are applied in a case study and provide valuable information on achievable assembly speedup.

LB4TL: A Smooth Semantics for Temporal Logic to Train Neural Feedback Controllers

This paper presents a framework for training neural network (NN)-based feedback controllers for autonomous agents with deterministic nonlinear dynamics to satisfy task objectives and safety constraints expressed in discrete-time Signal Temporal Logic (DT-STL). Control synthesis that uses the robustness semantics of DT-STL poses challenges due to its non-convexity, non-differentiability, and recursive definition, in particular when it is used to train NN-based controllers. We introduce a smooth neuro-symbolic computation graph to encode DT-STL robustness to represent a smooth approximation of the robustness, enabling the use of powerful stochastic gradient descent and backpropagation-based optimization for training. Our approximation guarantees that it lower bounds the robustness value of a given DT-STL formula, and shows orders of magnitude improvement over existing smooth approximations when applied to control synthesis. We demonstrate our approach on planning to satisfy complex spatio-temporal and sequential tasks, and show scalability with formula complexity.

SATF: A Scalable Attentive Transfer Framework for Efficient Multiagent Reinforcement Learning.

It is challenging to train an efficient learning procedure with multiagent reinforcement learning (MARL) when the number of agents increases as the observation space exponentially expands, especially in large-scale multiagent systems. In this article, we proposed a scalable attentive transfer framework (SATF) for efficient MARL, which achieved goals faster and more accurately in homogeneous and heterogeneous combat tasks by transferring learned knowledge from a small number of agents (4) to a large number of agents (up to 64). To reduce and align the dimensionality of the observed state variations caused by increasing numbers of agents, the proposed SATF deployed a novel state representation network with a self-attention mechanism, known as dynamic observation representation network (DorNet), to extract the dominant observed information with excellent cost-effectiveness. The experiments on the MAgent platform showed that the SATF outperformed the distributed MARL (independent Q-learning (IQL) and A2C) in task sequences from 8 to 64 agents. The experiments on StarCraft II showed that the SATF demonstrated superior performance relative to the centralized training with decentralized execution MARL (QMIX) by presenting shorter training steps, achieving a desired win rate of up to approximately 90% when increasing the number of agents from 4 to 32. The findings of our study showed the great potential for enhancing the efficiency of MARL training in large-scale agent combat missions.

A Systematic Review of Echo State Networks From Design to Application

Recurrent Neural Network (RNN) has demonstrated its outstanding ability in sequence tasks and has achieved state-of-the-art in many applications, such as industrial and medical. Echo State Network (ESN) is a simple type of RNN and has emerged in the last decade as an alternative to gradient descent training-based RNN. ESN is practical, conceptually simple, and easy to implement with a strong theoretical ground. It can avoid non-converging and computationally expensive issues in gradient descent RNN methods. Since ESN was put forward in 2002, abundant existing works have promoted the progress of ESN, and the recently introduced deep ESN opened the way to uniting the merits of deep learning and reservoir computing. Besides, the combinations of ESNs with other machine learning models have also overperformed baselines in some applications. However, the apparent simplicity of ESNs can sometimes be deceptive. Successfully applying ESNs needs some experience. Thus, we reviewed over 300 related papers and provided a systematic overview for the first time. In this paper, we categorize the related methods into classical ESN, DeepESN, and combination. Then, we analyze them from the perspective of network designs and specific applications. Finally, we discuss the challenges and opportunities by proposing open problems and future work.

Застосування віртуальної дошки miro для активізації навчальної діяльності на заняттях з медико-біологічних дисциплін

The work aim is to study the Miro interactive board use while learning biomedical disciplines by future PE teachers. Methods used in the work are practical, synthesis, analysis, comparison, and abstraction. The features of existing virtual boards used in the educational process are analyzed with a focus on their advantages and disadvantages. The potential of the Miro virtual board use for improving the educational process is highlighted: ease of use, multifunctionality, ample opportunities for creating various tasks and performing different kinds of activities (writing, sketching, drawing, calculations, etc.), providing educational material in an interesting and visual form, intensification of students’ learning activity and formation of a working atmosphere in lessons and positive emotions. The organizational, content, activity-related, and emotional components of work with the Miro virtual board are considered. The work studies the Miro online board’s abilities for active learning process organization in classes of biomedical disciplines for students – future PE teachers in higher education institutions. The peculiarities of creating matching tasks, sequence tasks, and tasks on object classification are considered. Methodological recommendations are provided for organizing various tasks involving texts, for creating association tasks including their preparation, peculiarities of use in lessons both for group and individual forms, and options for discussing results with students. Methodological requirements for the project activity implementation have been developed: selection of relevant research topics, creation of a poster template; comprehensive demonstration of work results, optimal and aesthetic design, organization of discussions, and making conclusions. Keywords: Miro online board, learning activity intensification, online learning, biomedical disciplines, higher education institutions.

A Game Theoretic Approach to Computation Offloading Strategy Optimization for Non-cooperative Users in Mobile Edge Computing

Computation offloading from a user equipment (UE, also called mobile user, mobile subscriber, or mobile device) to a mobile edge cloud (MEC) provides an effective way to virtualize an ordinary smart mobile device (e.g., smartphone, tablet, handheld computer, wearable device, and personal digital assistant) into a formidable equipment, which is able to provide more and stronger functionalities than that of a laptop or a desktop computer. It is conceivable that there can be several MECs with different processing capabilities in a geographic area, and each MEC many serve many UEs with endless sequences of computation tasks, various application characteristics, and diversified communication requirements and bandwidths. Furthermore, the mobile users are competitive and selfish, which means that computation offloading strategy optimization needs to be carried out for each individual mobile user to optimize the performance of only his applications. In this paper, we conduct a mathematical study of computation offloading strategy optimization for non-cooperative users in mobile edge computing by using a game theoretic approach. The main contributions of this paper can be summarized as follows. We establish an M/G/1 queueing model to characterize multiple heterogeneous UEs and MECs, so that the average response time of all offloadable and non-offloadable tasks generated on a UE can be calculated analytically and the optimal computation offloading strategy of a UE can be defined rigorously. We construct a non-cooperative game framework for a mobile edge computing environment, in which each player (i.e., a UE) can selfishly minimize his payoff by choosing an appropriate strategy in his strategy space. We prove the existence of the Nash equilibrium of the above game. We develop algorithms to find the Nash equilibrium, including an algorithm to find the best response of a mobile user and an iterative algorithm to find the Nash equilibrium. We demonstrate numerical examples and data of our game, including numerical data for the Nash equilibrium and numerical data for the convergence of the Nash equilibrium. To the best of the author's knowledge, this is the first paper that effectively investigates computation offloading strategy optimization for multiple, heterogeneous, and competitive mobile users and multiple heterogeneous mobile edge clouds by using a non-cooperative game approach. Hence, the paper makes noticeable contributions towards the understanding of a competing mobile edge computing environment and its stabilization.

Optimal Task and Motion Planning and Execution for Multiagent Systems in Dynamic Environments.

Combining symbolic and geometric reasoning in multiagent systems is a challenging task that involves planning, scheduling, and synchronization problems. Existing works overlooked the variability of task duration and geometric feasibility intrinsic to these systems because of the interaction between agents and the environment. We propose a combined task and motion planning approach to optimize the sequencing, assignment, and execution of tasks under temporal and spatial variability. The framework relies on decoupling tasks and actions, where an action is one possible geometric realization of a symbolic task. At the task level, timeline-based planning deals with temporal constraints, duration variability, and synergic assignment of tasks. At the action level, online motion planning plans for the actual movements dealing with environmental changes. We demonstrate the approach's effectiveness in a collaborative manufacturing scenario, in which a robotic arm and a human worker shall assemble a mosaic in the shortest time possible. Compared with existing works, our approach applies to a broader range of applications and reduces the execution time of the process.

On the Benefit of Optimal Transport for Curriculum Reinforcement Learning.

Curriculum reinforcement learning (CRL) allows solving complex tasks by generating a tailored sequence of learning tasks, starting from easy ones and subsequently increasing their difficulty. Although the potential of curricula in RL has been clearly shown in various works, it is less clear how to generate them for a given learning environment, resulting in various methods aiming to automate this task. In this work, we focus on framing curricula as interpolations between task distributions, which has previously been shown to be a viable approach to CRL. Identifying key issues of existing methods, we frame the generation of a curriculum as a constrained optimal transport problem between task distributions. Benchmarks show that this way of curriculum generation can improve upon existing CRL methods, yielding high performance in various tasks with different characteristics.

SegMorph: Concurrent Motion Estimation and Segmentation for Cardiac MRI Sequences.

We propose a novel recurrent variational network, SegMorph, to perform concurrent segmentation and motion estimation on cardiac cine magnetic resonance image (CMR) sequences. Our model establishes a recurrent latent space that captures spatiotemporal features from cine-MRI sequences for multitask inference and synthesis. The proposed model follows a recurrent variational auto-encoder framework and adopts a learnt prior from the temporal inputs. We utilise a multi-branch decoder to handle bi-ventricular segmentation and motion estimation simultaneously. In addition to the spatiotemporal features from the latent space, motion estimation enriches the supervision of sequential segmentation tasks by providing pseudo-ground truth. On the other hand, the segmentation branch helps with motion estimation by predicting deformation vector fields (DVFs) based on anatomical information. Experimental results demonstrate that the proposed method performs better than state-of-the-art approaches qualitatively and quantitatively for both segmentation and motion estimation tasks. We achieved an 81% average Dice Similarity Coefficient (DSC) and a less than 3.5 mm average Hausdorff distance on segmentation. Meanwhile, we achieved a motion estimation Dice Similarity Coefficient of over 79%, with approximately 0.14% of pixels displaying a negative Jacobian determinant in the estimated DVFs.

Variations of Training Process in Vanilla Recurrent Neural Network Framework

Recurrent neural networks (RNNs) are capable of learning features and long term dependencies from sequential and time series data and show outstanding performance in sequential modeling tasks. However, training process in RNNs is troubled by issues in learning processes such as slow inference, vanishing gradients and difficulties in capturing long term dependencies. In this paper, we introduce a new learning technique to update the weight set as we change the input sequence which is shifted by certain amount of time in training process, instead of using a traditional way to calculate one set of the weights and bias in training time series with sequences shifted by certain amount of time series. We also consider an algorithm for an evaluation process. In the traditional way, the evaluation process is executed by using final weights and biases calculated in the training process. Instead, during the testing process, the weights and biases are iteratively updated in each sequence as done in the training process. Several numerical experiments demonstrate the efficiency of the proposed techniques.

GC2: Generalizable Continual Classification of Medical Images.

Deep learning models have achieved remarkable success in medical image classification. These models are typically trained once on the available annotated images and thus lack the ability of continually learning new tasks (i.e., new classes or data distributions) due to the problem of catastrophic forgetting. Recently, there has been more interest in designing continual learning methods to learn different tasks presented sequentially over time while preserving previously acquired knowledge. However, these methods focus mainly on preventing catastrophic forgetting and are tested under a closed-world assumption; i.e., assuming the test data is drawn from the same distribution as the training data. In this work, we advance the state-of-the-art in continual learning by proposing GC2 for medical image classification, which learns a sequence of tasks while simultaneously enhancing its out-of-distribution robustness. To alleviate forgetting, GC2 employs a gradual culpability-based network pruning to identify an optimal subnetwork for each task. To improve generalization, GC2 incorporates adversarial image augmentation and knowledge distillation approaches for learning generalized and robust representations for each subnetwork. Our extensive experiments on multiple benchmarks in a task-agnostic inference demonstrate that GC2 significantly outperforms baselines and other continual learning methods in reducing forgetting and enhancing generalization. Our code is publicly available at the following link: https://github.com/ nourhanb/TMI2024-GC2.

Lifelong Learning With Cycle Memory Networks.

Learning from a sequence of tasks for a lifetime is essential for an agent toward artificial general intelligence. Despite the explosion of this research field in recent years, most work focuses on the well-known catastrophic forgetting issue. In contrast, this work aims to explore knowledge-transferable lifelong learning without storing historical data and significant additional computational overhead. We demonstrate that existing data-free frameworks, including regularization-based single-network and structure-based multinetwork frameworks, face a fundamental issue of lifelong learning, named anterograde forgetting, i.e., preserving and transferring memory may inhibit the learning of new knowledge. We attribute it to the fact that the learning network capacity decreases while memorizing historical knowledge and conceptual confusion between the irrelevant old knowledge and the current task. Inspired by the complementary learning theory in neuroscience, we endow artificial neural networks with the ability to continuously learn without forgetting while recalling historical knowledge to facilitate learning new knowledge. Specifically, this work proposes a general framework named cycle memory networks (CMNs). The CMN consists of two individual memory networks to store short-and long-term memories separately to avoid capacity shrinkage and a transfer cell between them. It enables knowledge transfer from the long-term to the short-term memory network to mitigate conceptual confusion. In addition, the memory consolidation mechanism integrates short-term knowledge into the long-term memory network for knowledge accumulation. We demonstrate that the CMN can effectively address the anterograde forgetting on several task-related, task-conflict, class-incremental, and cross-domain benchmarks. Furthermore, we provide extensive ablation studies to verify each framework component. The source codes are available at: https://github.com/GeoX-Lab/CMN.

Continual Residual Reservoir Computing for Remaining Useful Life Prediction

In practical engineering applications, it is inevitable that the production is often faced with different working conditions. Therefore, it is necessary to have a continual learning system, which can adapt to a sequence of tasks and keep learning over the time. In this work, we propose a continual deep residual reservoir computing (DRRC) framework for the practical remaining useful life (RUL) prediction task. Specifically, we propose a novel deep echo state network structure with residual blocks to effectively mitigate the performance degradation of the deep reservoir computing framework and reduce the difficulty of model training. Further, the proposed framework is trained with the elastic weight consolidation (EWC) method to alleviate the impact of catastrophic forgetting in continual learning systems. Extensive experiments are conducted with the FEMTO-ST bearing and high intensity radiated fields (HIRF) battery dataset. And the proposed framework is proved to be effective in multiple continual learning tasks comparing with other state-of-the-art methods.

Bidirectional Progressive Neural Networks With Episodic Return Progress for Emergent Task Sequencing and Robotic Skill Transfer

Bidirectional Progressive Neural Networks With Episodic Return Progress for Emergent Task Sequencing and Robotic Skill Transfer

Collaborative human-centered design of manufacturing tasks: a multi-user immersive VR experience

Work-related musculoskeletal disorders are among the top factors impacting the individual’s performance and the overall company’s productivity. Virtual Reality (VR) has enabled proactive consideration of human factors. However, there are still barriers impeding the broader adoption of human-in-the-loop approaches, including the number and roles of people involved in simulation stages and the complexity of modelling lengthy task sequences. This paper presents a multi-user immersive VR simulation framework for collaborative human-centered task evaluation involving engineers and operators. The software architecture enabling multi-user VR sessions is discussed, together with a hierarchical approach for modelling complex manufacturing tasks in VR applications and collecting structured data from the simulations. Metrics such as heatmap and Rapid Upper Limb Assessment are integrated for informed decision-making about task redesign. The proposed approach was tested in a case study inspired by large parts manufacturing, where operators need to work in teams. The server-client network enabled the engineer to comprehensively assess the design of the task having two operators executing virtual actions in parallel as they would in the actual workstation. The collection of data from the team of operators and their intuitive visualization enhanced the effectiveness in identifying aspects introducing discomfort and assessing the overall suitability of the design for human operators.

Scheduling a Single-Arm Two-Cluster Tool With a Process Module Failure Subject to Wafer Residency Time Constraints

Multi-cluster tools are widely adopted in semiconductor manufacturing. When a process module (PM) at a step fails, a multi-cluster tool cannot complete the process recipe of work-in-process wafers and must be forced to enter a closedown process to be empty. To increase the throughput of a wafer fab, it is economically significant to shorten the failure-closedown process. However, due to the wafer residency time constraints, it is highly challenging to respond to a PM failure and find a corresponding optimal schedule. By assuming no parallel PM at a step, this work is the first to study this important issue for scheduling multi-cluster tools. We analyze the task sequences and synchronization conditions for robot activities to avoid deadlock in a shared buffer module. Upon these analyses, for process-dominant multi-cluster tools whose optimal steady-state schedule is known, algorithms are proposed to synthesize the proper sequences for robots in case of PM failures, then, a nonlinear program model is proposed to find an optimal schedule for the corresponding closedown process or decide no feasible solutions. The proposed model can uniformly deal with different scenarios of PM failures. Examples are given to illustrate the application of the proposed method. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —In a wafer fab, there are hundreds, even thousands, of cluster tools. It is common that a failure of a processing module happens in a cluster tool. How to intelligently respond to such a random failure in a multi-cluster tool is an important issue in real-world production. This paper studies the scheduling problem of a multi-cluster tool in case of a failure at a PM. For a multi-cluster tool in case of a failure module, the proposed method can significantly reduce the loss of work-in-process wafers and shorten the closedown process.

A Multi-Level Task Framework for Event Sequence Analysis.

Despite the development of numerous visual analytics tools for event sequence data across various domains, including but not limited to healthcare, digital marketing, and user behavior analysis, comparing these domain-specific investigations and transferring the results to new datasets and problem areas remain challenging. Task abstractions can help us go beyond domain-specific details, but existing visualization task abstractions are insufficient for event sequence visual analytics because they primarily focus on multivariate datasets and often overlook automated analytical techniques. To address this gap, we propose a domain-agnostic multi-level task framework for event sequence analytics, derived from an analysis of 58 papers that present event sequence visualization systems. Our framework consists of four levels: objective, intent, strategy, and technique. Overall objectives identify the main goals of analysis. Intents comprises five high-level approaches adopted at each analysis step: augment data, simplify data, configure data, configure visualization, and manage provenance. Each intent is accomplished through a number of strategies, for instance, data simplification can be achieved through aggregation, summarization, or segmentation. Finally, each strategy can be implemented by a set of techniques depending on the input and output components. We further show that each technique can be expressed through a quartet of action-input-output-criteria. We demonstrate the framework's descriptive power through case studies and discuss its similarities and differences with previous event sequence task taxonomies.

Dual Balanced Class-Incremental Learning With im-Softmax and Angular Rectification.

Owing to the superior performances, exemplar-based methods with knowledge distillation (KD) are widely applied in class incremental learning (CIL). However, it suffers from two drawbacks: 1) data imbalance between the old/learned and new classes causes the bias of the new classifier toward the head/new classes and 2) deep neural networks (DNNs) suffer from distribution drift when learning sequence tasks, which results in narrowed feature space and deficient representation of old tasks. For the first problem, we analyze the insufficiency of softmax loss when dealing with the problem of data imbalance in theory and then propose the imbalance softmax (im-softmax) loss to relieve the imbalanced data learning, where we re-scale the output logits to underfit the head/new classes. For another problem, we calibrate the feature space by incremental-adaptive angular margin (IAAM) loss. The new classes form a complete distribution in feature space yet the old are squeezed. To recover the old feature space, we first compute the included angle of normalized features and normalized anchor prototypes, and use the angle distribution to represent the class distribution, then we replenish the old distribution with the deviation from the new. Each anchor prototype is predefined as a learnable vector for a designated class. The proposed im-softmax reduces the bias in the linear classification layer. IAAM rectifies the representation learning, reduces the intra-class distance, and enlarges the inter-class margin. Finally, we seamlessly combine the im-softmax and IAAM in an end-to-end training framework, called the dual balanced class incremental learning (DBL), for further improvements. Experiments demonstrate the proposed method achieves state-of-the-art (SOTA) performances on several benchmarks, such as CIFAR10, CIFAR100, Tiny-ImageNet, and ImageNet-100.

Identifying Transfer Learning in the Reshaping of Inductive Biases.

Transfer learning, the reuse of newly acquired knowledge under novel circumstances, is a critical hallmark of human intelligence that has frequently been pitted against the capacities of artificial learning agents. Yet, the computations relevant to transfer learning have been little investigated in humans. The benefit of efficient inductive biases (meta-level constraints that shape learning, often referred as priors in the Bayesian learning approach), has been both theoretically and experimentally established. Efficiency of inductive biases depends on their capacity to generalize earlier experiences. We argue that successful transfer learning upon task acquisition is ensured by updating inductive biases and transfer of knowledge hinges upon capturing the structure of the task in the inductive bias that can be reused in novel tasks. To explore this, we trained participants on a non-trivial visual stimulus sequence task (Alternating Serial Response Times, ASRT); during the Training phase, participants were exposed to one specific sequence for multiple days, then on the Transfer phase, the sequence changed, while the underlying structure of the task remained the same. Our results show that beyond the acquisition of the stimulus sequence, our participants were also able to update their inductive biases. Acquisition of the new sequence was considerably sped up by earlier exposure but this enhancement was specific to individuals showing signatures of abandoning initial inductive biases. Enhancement of learning was reflected in the development of a new internal model. Additionally, our findings highlight the ability of participants to construct an inventory of internal models and alternate between them based on environmental demands. Further, investigation of the behavior during transfer revealed that it is the subjective internal model of individuals that can predict the transfer across tasks. Our results demonstrate that even imperfect learning in a challenging environment helps learning in a new context by reusing the subjective and partial knowledge about environmental regularities.