Sequential Task Research Articles

Dopamine D2 Receptor Modulates Exercise Related Effect on Cortical Excitation/Inhibition and Motor Skill Acquisition.

Exercise is known to benefit motor skill learning in health and neurological disease. Evidence from brain stimulation, genotyping, and Parkinson's disease studies converge to suggest that the dopamine D2 receptor, and shifts in the cortical excitation and inhibition (E:I) balance, are prime candidates for the drivers of exercise-enhanced motor learning. However, causal evidence using experimental pharmacological challenge is lacking. We hypothesized that the modulatory effect of the dopamine D2 receptor on exercise-induced changes in the E:I balance would determine the magnitude of motor skill acquisition. To test this, we measured exercise-induced changes in excitation and inhibition using paired-pulse transcranial magnetic stimulation (TMS) in 22 healthy female and male humans, and then had participants learn a novel motor skill-the sequential visual isometric pinch task (SVIPT). We examined the effect of D2 receptor blockade (800 mg sulpiride) on these measures within a randomized, double-blind, placebo-controlled design. Our key result was that motor skill acquisition was driven by an interaction between the D2 receptor and E:I balance. Specifically, poorer skill learning was related to an attenuated shift in the E:I balance in the sulpiride condition, whereas this interaction was not evident in placebo. Our results demonstrate that exercise-primed motor skill acquisition is causally influenced by D2 receptor activity on motor cortical circuits.

USER EXPERIENCE (UX) DESIGN IN MEDICAL PRODUCTS: THEORETICAL FOUNDATIONS AND DEVELOPMENT BEST PRACTICES

User Experience (UX) Design in Medical Products is pivotal in enhancing patient outcomes, satisfaction, and adherence to treatment regimens. This abstract delves into the theoretical underpinnings and best practices that underscore effective UX design within the medical domain. Grounded in human-centered design principles, this approach emphasizes understanding user needs, preferences, and limitations to develop inclusive, accessible, and intuitive interfaces. Integrating insights from behavioral psychology, UX designers leverage techniques such as persuasive design to promote healthy behaviors and facilitate adherence to medical protocols. Moreover, compliance with regulatory standards is paramount, necessitating a nuanced understanding of medical regulations and standards to ensure product safety and efficacy. Usability testing emerges as a crucial step, facilitating iterative improvements based on user feedback and ensuring that medical products are intuitive, error-resistant, and conducive to safe user interactions. Beyond functionality, considerations of data privacy and security are paramount, requiring UX designers to implement robust measures to safeguard patient confidentiality while maintaining seamless user experiences. Communication between patients and healthcare providers is also a focal point, with UX strategies aimed at enhancing information exchange, fostering trust, and facilitating informed decision-making. Additionally, optimizing workflow efficiency through streamlined task sequences and leveraging emerging technologies such as artificial intelligence and augmented reality further enhances the user experience in medical contexts. Through continual iteration and refinement, UX design in medical products strives to deliver compassionate, user-centric solutions that meet the diverse needs of patients and healthcare professionals alike, ultimately driving improved healthcare delivery and patient outcomes.
 Keywords: User Experience Design, Medical Products, Human-Centered Design, Behavioral Psychology, Regulatory Compliance, Usability Testing.

Remaining useful life estimation of bearing via temporal convolutional networks enhanced by a gated convolutional unit

In the field of prognostics and health management (PHM) for industrial equipment and systems, the estimation of remaining useful life (RUL) constitutes a fundamental task. A reliable and accurate method for estimating the RUL is therefore essential. This paper proposes a dynamic self-adaptive ensemble model, aimed at improving the rolling bearing RUL prediction. This model integrates an adaptive multi-scale feature extractor, a gated convolutional unit (GCU) and temporal convolutional networks (TCN). Through a redesign of the data flow, this model directly incorporates multi-scale comprehensive feature evaluation indicators into the neural network data flow, significantly enhancing the model's feature extraction capabilities. Subsequently, the study extends the traditional TCN by incorporating the GCU module and its gating mechanisms, further strengthening the model's capacity to capture long-term dependencies in sequence tasks. Experimental results demonstrate that, compared to existing state-of-the-art (SOTA) models, our method achieves at least a 10% increase in the prediction accuracy on two public run-to-failure bearing datasets. Beyond the tested datasets, the architecture that directly maps multi-scale evaluation indicators into the structure of neural network data flows also holds potential for broader application across diverse PHM tasks, promising significant improvements in the industrial safety and efficiency.

Cloud-edge-end workflow scheduling with multiple privacy levels

The cloud-edge-end architecture satisfies the execution requirements of various workflow applications. However, owing to the diversity of resources, the complex hierarchical structure, and different privacy requirements for users, determining how to lease suitable cloud-edge-end resources, schedule multi-privacy-level workflow tasks, and optimize leasing costs is currently one of the key challenges in cloud computing. In this paper, we address the scheduling optimization problem of workflow applications containing tasks with multiple privacy levels. To tackle this problem, we propose a heuristic privacy-preserving workflow scheduling algorithm (PWHSA) designed to minimize rental costs which includes time parameter estimation, task sub-deadline division, scheduling sequence generation, task scheduling, and task adjustment, with candidate strategies developed for each component. These candidate strategies in each step undergo statistical calibration across a comprehensive set of workflow instances. We compare the proposed algorithm with modified classical algorithms that target similar problems. The experimental results demonstrate that the PWHSA algorithm outperforms the comparison algorithms while maintaining acceptable execution times.

Can you tell people’s cognitive ability level from their response patterns in questionnaires?

Questionnaires are ever present in survey research. In this study, we examined whether an indirect indicator of general cognitive ability could be developed based on response patterns in questionnaires. We drew on two established phenomena characterizing connections between cognitive ability and people’s performance on basic cognitive tasks, and examined whether they apply to questionnaires responses. (1) The worst performance rule (WPR) states that people’s worst performance on multiple sequential tasks is more indicative of their cognitive ability than their average or best performance. (2) The task complexity hypothesis (TCH) suggests that relationships between cognitive ability and performance increase with task complexity. We conceptualized items of a questionnaire as a series of cognitively demanding tasks. A graded response model was used to estimate respondents’ performance for each item based on the difference between the observed and model-predicted response (“response error” scores). Analyzing data from 102 items (21 questionnaires) collected from a large-scale nationally representative sample of people aged 50+ years, we found robust associations of cognitive ability with a person’s largest but not with their smallest response error scores (supporting the WPR), and stronger associations of cognitive ability with response errors for more complex than for less complex questions (supporting the TCH). Results replicated across two independent samples and six assessment waves. A latent variable of response errors estimated for the most complex items correlated .50 with a latent cognitive ability factor, suggesting that response patterns can be utilized to extract a rough indicator of general cognitive ability in survey research.

Modeling Adaptive Inter-Task Feature Interactions via Sentiment-Aware Contrastive Learning for Joint Aspect-Sentiment Prediction

Aspect prediction (AP) and sentiment prediction (SP) are representative applications in fine-grained sentiment anal- ysis. They can be considered as sequential tasks, where AP identifies mentioned aspects in a sentence, and SP infers fine-grained sentiments for these aspects. Recent models perform the aspect-sentiment prediction in a joint man-ner, but heavily rely on the feature interactions of aspect and sentiment. One drawback is that they ignore correlation strength varies between aspect features and sentiment fea- tures across different sentences, and employ a fixed feature interaction strategy may limit effective knowledge transfer across tasks. To tackle this issue, in this paper, we propose an Adaptive Inter-task Feature Interaction framework, AIFI, for joint aspect-sentiment prediction. Specifically, we introduce a novel contrast-based alignment method based on contrastive learning. Our approach considers the AP-specific and SP-specific representations of a given sentence as a positive pair, while representation of another random sentence serves as a negative example. Moreover, we propose an inter-task feature correlation network to predict the contrast strength, which is determined by the temperature coefficient in the InfoNCE loss. This dynamic correlation adjustment enhances model’s ability to capture proper feature interactions more efficiently. Experimental results on three datasets validate the effectiveness of our approach.

Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding

Deep neural networks are susceptible to catastrophic forgetting when trained on sequential tasks. Various continual learning (CL) methods often rely on exemplar buffers or/and network expansion for balancing model stability and plasticity, which, however, compromises their practical value due to privacy and memory concerns. Instead, this paper considers a strict yet realistic setting, where the training data from previous tasks is unavailable and the model size remains relatively constant during sequential training. To achieve such desiderata, we propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. This is achieved by the synergy between two key components: HSIC-Bottleneck Orthogonalization (HBO) implements non-overwritten parameter updates mediated by Hilbert-Schmidt independence criterion in an orthogonal space and EquiAngular Embedding (EAE) enhances decision boundary adaptation between old and new tasks with predefined basis vectors. Extensive experiments demonstrate that our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.

Unify Named Entity Recognition Scenarios via Contrastive Real-Time Updating Prototype

Supervised named entity recognition (NER) aims to classify entity mentions into a fixed number of pre-defined types. However, in real-world scenarios, unknown entity types are continually involved. Naive fine-tuning will result in catastrophic forgetting on old entity types. Existing continual methods usually depend on knowledge distillation to alleviate forgetting, which are less effective on long task sequences. Moreover, most of them are specific to the class-incremental scenario and cannot adapt to the online scenario, which is more common in practice. In this paper, we propose a unified framework called Contrastive Real-time Updating Prototype (CRUP) that can handle different scenarios for NER. Specifically, we train a Gaussian projection model by a regularized contrastive objective. After training on each batch, we store the mean vectors of representations belong to new entity types as their prototypes. Meanwhile, we update existing prototypes belong to old types only based on representations of the current batch. The final prototypes will be used for the nearest class mean classification. In this way, CRUP can handle different scenarios through its batch-wise learning. Moreover, CRUP can alleviate forgetting in continual scenarios only with current data instead of old data. To comprehensively evaluate CRUP, we construct extensive benchmarks based on various datasets. Experimental results show that CRUP significantly outperforms baselines in continual scenarios and is also competitive in the supervised scenario.

Proxyformer: Nyström-Based Linear Transformer with Trainable Proxy Tokens

Transformer-based models have demonstrated remarkable performance in various domains, including natural language processing, image processing and generative modeling. The most significant contributor to the successful performance of Transformer models is the self-attention mechanism, which allows for a comprehensive understanding of the interactions between tokens in the input sequence. However, there is a well-known scalability issue, the quadratic dependency (i.e. O(n^2)) of self-attention operations on the input sequence length n, making the handling of lengthy sequences challenging. To address this limitation, there has been a surge of research on efficient transformers, aiming to alleviate the quadratic dependency on the input sequence length. Among these, the Nyströmformer, which utilizes the Nyström method to decompose the attention matrix, achieves superior performance in both accuracy and throughput. However, its landmark selection exhibits redundancy, and the model incurs computational overhead when calculating the pseudo-inverse matrix. We propose a novel Nyström method-based transformer, called Proxyformer. Unlike the traditional approach of selecting landmarks from input tokens, the Proxyformer utilizes trainable neural memory, called proxy tokens, for landmarks. By integrating contrastive learning, input injection, and a specialized dropout for the decomposed matrix, Proxyformer achieves top-tier performance for long sequence tasks in the Long Range Arena benchmark.

E2E-AT: A Unified Framework for Tackling Uncertainty in Task-Aware End-to-End Learning

Successful machine learning involves a complete pipeline of data, model, and downstream applications. Instead of treating them separately, there has been a prominent increase of attention within the constrained optimization (CO) and machine learning (ML) communities towards combining prediction and optimization models. The so-called end-to-end (E2E) learning captures the task-based objective for which they will be used for decision making. Although a large variety of E2E algorithms have been presented, it has not been fully investigated how to systematically address uncertainties involved in such models. Most of the existing work considers the uncertainties of ML in the input space and improves robustness through adversarial training. We extend this idea to E2E learning and prove that there is a robustness certification procedure by solving augmented integer programming. Furthermore, we show that neglecting the uncertainty of COs during training causes a new trigger for generalization errors. To include all these components, we propose a unified framework that covers the uncertainties emerging in both the input feature space of the ML models and the COs. The framework is described as a robust optimization problem and is practically solved via end-to-end adversarial training (E2E-AT). Finally, the performance of E2E-AT is evaluated by a real-world end-to-end power system operation problem, including load forecasting and sequential scheduling tasks.

Improve Robustness of Reinforcement Learning against Observation Perturbations via l∞ Lipschitz Policy Networks

Deep Reinforcement Learning (DRL) has achieved remarkable advances in sequential decision tasks. However, recent works have revealed that DRL agents are susceptible to slight perturbations in observations. This vulnerability raises concerns regarding the effectiveness and robustness of deploying such agents in real-world applications. In this work, we propose a novel robust reinforcement learning method called SortRL, which improves the robustness of DRL policies against observation perturbations from the perspective of the network architecture. We employ a novel architecture for the policy network that incorporates global $l_\infty$ Lipschitz continuity and provide a convenient method to enhance policy robustness based on the output margin. Besides, a training framework is designed for SortRL, which solves given tasks while maintaining robustness against $l_\infty$ bounded perturbations on the observations. Several experiments are conducted to evaluate the effectiveness of our method, including classic control tasks and video games. The results demonstrate that SortRL achieves state-of-the-art robustness performance against different perturbation strength.

MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA

Large language models (LLMs) have shown great success in various Natural Language Processing (NLP) tasks, whist they still need updates after deployment to fix errors or keep pace with the changing knowledge in the world. Researchers formulate such problem as Model Editing and have developed various editors focusing on different axes of editing properties. However, current editors can hardly support all properties and rely on heavy computational resources. In this paper, we propose a plug-in Model Editing method based on neuron-indexed dynamic LoRA (MELO), which alters the behavior of language models by dynamically activating certain LoRA blocks according to the index built in an inner vector database. Our method satisfies various editing properties with high efficiency and can be easily integrated into multiple LLM backbones. Experimental results show that our proposed MELO achieves state-of-the-art editing performance on three sequential editing tasks (document classification, question answering and hallucination correction), while requires the least trainable parameters and computational cost.

Learning to Prompt Knowledge Transfer for Open-World Continual Learning

This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL). OwCL is increasingly rising while it is highly challenging in two-fold: i) learning a sequence of tasks without forgetting knowns in the past, and ii) identifying unknowns (novel objects/classes) in the future. Existing OwCL methods suffer from the adaptability of task-aware boundaries between knowns and unknowns, and do not consider the mechanism of knowledge transfer. In this work, we propose Pro-KT, a novel prompt-enhanced knowledge transfer model for OwCL. Pro-KT includes two key components: (1) a prompt bank to encode and transfer both task-generic and task-specific knowledge, and (2) a task-aware open-set boundary to identify unknowns in the new tasks. Experimental results using two real-world datasets demonstrate that the proposed Pro-KT outperforms the state-of-the-art counterparts in both the detection of unknowns and the classification of knowns markedly. Code released at https://github.com/YujieLi42/Pro-KT.

PORTAL: Automatic Curricula Generation for Multiagent Reinforcement Learning

Despite many breakthroughs in recent years, it is still hard for MultiAgent Reinforcement Learning (MARL) algorithms to directly solve complex tasks in MultiAgent Systems (MASs) from scratch. In this work, we study how to use Automatic Curriculum Learning (ACL) to reduce the number of environmental interactions required to learn a good policy. In order to solve a difficult task, ACL methods automatically select a sequence of tasks (i.e., curricula). The idea is to obtain maximum learning progress towards the final task by continuously learning on tasks that match the current capabilities of the learners. The key question is how to measure the learning progress of the learner for better curriculum selection. We propose a novel ACL framework, PrOgRessive mulTiagent Automatic curricuLum (PORTAL), for MASs. PORTAL selects curricula according to two critera: 1) How difficult is a task, relative to the learners’ current abilities? 2) How similar is a task, relative to the final task? By learning a shared feature space between tasks, PORTAL is able to characterize different tasks based on the distribution of features and select those that are similar to the final task. Also, the shared feature space can effectively facilitate the policy transfer between curricula. Experimental results show that PORTAL can train agents to master extremely hard cooperative tasks, which can not be achieved with previous state-of-the-art MARL algorithms.

GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation

Offline imitation learning (IL) refers to learning expert behavior solely from demonstrations, without any additional interaction with the environment. Despite significant advances in offline IL, existing techniques find it challenging to learn policies for long-horizon tasks and require significant re-training when task specifications change. Towards addressing these limitations, we present GO-DICE an offline IL technique for goal-conditioned long-horizon sequential tasks. GO-DICE discerns a hierarchy of sub-tasks from demonstrations and uses these to learn separate policies for sub-task transitions and action execution, respectively; this hierarchical policy learning facilitates long-horizon reasoning.Inspired by the expansive DICE-family of techniques, policy learning at both the levels transpires within the space of stationary distributions. Further, both policies are learnt with goal conditioning to minimize need for retraining when task goals change. Experimental results substantiate that GO-DICE outperforms recent baselines, as evidenced by a marked improvement in the completion rate of increasingly challenging pick-and-place Mujoco robotic tasks. GO-DICE is also capable of leveraging imperfect demonstration and partial task segmentation when available, both of which boost task performance relative to learning from expert demonstrations alone.

Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses. Implementing online training of RNNs on the edge calls for optimized algorithms for an efficient deployment on hardware. Inspired by the spiking neuron model, the Delta RNN exploits temporal sparsity during inference by skipping over the update of hidden states from those inactivated neurons whose change of activation across two timesteps is below a defined threshold. This work describes a training algorithm for Delta RNNs that exploits temporal sparsity in the backward propagation phase to reduce computational requirements for training on the edge. Due to the symmetric computation graphs of forward and backward propagation during training, the gradient computation of inactivated neurons can be skipped. Results show a reduction of ∼80% in matrix operations for training a 56k parameter Delta LSTM on the Fluent Speech Commands dataset with negligible accuracy loss. Logic simulations of a hardware accelerator designed for the training algorithm show 2-10X speedup in matrix computations for an activation sparsity range of 50%-90%. Additionally, we show that the proposed Delta RNN training will be useful for online incremental learning on edge devices with limited computing resources.

Lifetime policy reuse and the importance of task capacity

A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks while avoiding catastrophic forgetting. Policy reuse and other multi-policy reinforcement learning techniques can learn multiple tasks but may generate many policies. This paper presents two novel contributions, namely 1) Lifetime Policy Reuse, a model-agnostic policy reuse algorithm that avoids generating many policies by optimising a fixed number of near-optimal policies through a combination of policy optimisation and adaptive policy selection; and 2) the task capacity, a measure for the maximal number of tasks that a policy can accurately solve. Comparing two state-of-the-art base-learners, the results demonstrate the importance of Lifetime Policy Reuse and task capacity based pre-selection on an 18-task partially observable Pacman domain and a Cartpole domain of up to 125 tasks.

Unsupervised question-retrieval approach based on topic keywords filtering and multi-task learning

Currently, the majority of retrieval-based question-answering systems depend on supervised training using question pairs. However, there is still a significant need for further exploration of how to employ unsupervised methods to improve the accuracy of retrieval-based question-answering systems. From the perspective of question topic keywords, this paper presents TFCSG, an unsupervised question-retrieval approach based on topic keyword filtering and multi-task learning. Firstly, we design the topic keyword filtering algorithm, which, unlike the topic model, can sequentially filter out the keywords of the question and can provide a training corpus for subsequent unsupervised learning. Then, three tasks are designed in this paper to complete the training of the question-retrieval model. The first task is a question contrastive learning task based on topic keywords repetition strategy, the second is questions and its corresponding sequential topic keywords similarity distribution task, and the third is a sequential topic keywords generation task using questions. These three tasks are trained in parallel in order to obtain quality question representations and thus improve the accuracy of question-retrieval task. Finally, our experimental results on the four publicly available datasets demonstrate the effectiveness of the TFCSG, with an average improvement of 7.1%, 4.4%, and 3.5% in the P@1, MAP, and MRR metrics when using the BERT model compared to the baseline model. The corresponding metrics improved by 5.7%, 3.5% and 3.0% on average when using the RoBERTa model. The accuracy of unsupervised similar question-retrieval task is effectively improved. In particular, the values of P@1, P@5, and P@10 are close, the retrieved similar questions are ranked more advance.

Optimization of news dissemination push mode by intelligent edge computing technology for deep learning

The Internet era is an era of information explosion. By 2022, the global Internet users have reached more than 4 billion, and the social media users have exceeded 3 billion. People face a lot of news content every day, and it is almost impossible to get interesting information by browsing all the news content. Under this background, personalized news recommendation technology has been widely used, but it still needs to be further optimized and improved. In order to better push the news content of interest to different readers, users' satisfaction with major news websites should be further improved. This study proposes a new recommendation algorithm based on deep learning and reinforcement learning. Firstly, the RL algorithm is introduced based on deep learning. Deep learning is excellent in processing large-scale data and complex pattern recognition, but it often faces the challenge of low sample efficiency when it comes to complex decision-making and sequential tasks. While reinforcement learning (RL) emphasizes learning optimization strategies through continuous trial and error through interactive learning with the environment. Compared with deep learning, RL is more suitable for scenes that need long-term decision-making and trial-and-error learning. By feeding back the reward signal of the action, the system can better adapt to the unknown environment and complex tasks, which makes up for the relative shortcomings of deep learning in these aspects. A scenario is applied to an action to solve the sequential decision problem in the news dissemination process. In order to enable the news recommendation system to consider the dynamic changes in users' interest in news content, the Deep Deterministic Policy Gradient algorithm is applied to the news recommendation scenario. Opposing learning complements and combines Deep Q-network with the strategic network. On the basis of fully summarizing and thinking, this paper puts forward the mode of intelligent news dissemination and push. The push process of news communication information based on edge computing technology is proposed. Finally, based on Area Under Curve a Q-Leaning Area Under Curve for RL models is proposed. This indicator can measure the strengths and weaknesses of RL models efficiently and facilitates comparing models and evaluating offline experiments. The results show that the DDPG algorithm improves the click-through rate by 2.586% compared with the conventional recommendation algorithm. It shows that the algorithm designed in this paper has more obvious advantages in accurate recommendation by users. This paper effectively improves the efficiency of news dissemination by optimizing the push mode of intelligent news dissemination. In addition, the paper also deeply studies the innovative application of intelligent edge technology in news communication, which brings new ideas and practices to promote the development of news communication methods. Optimizing the push mode of intelligent news dissemination not only improves the user experience, but also provides strong support for the application of intelligent edge technology in this field, which has important practical application prospects.

Micro-consolidation occurs when learning an implicit motor sequence, but is not influenced by HIIT exercise

We investigated if micro-consolidation, a phenomenon recently discovered during the brief rest periods between practice when learning an explicit motor sequence, generalises to learning an implicit motor sequence task. We demonstrate micro-consolidation occurs in the absence of explicit sequence awareness. We also investigated the effect of a preceding bout of high-intensity exercise, as exercise is known to augment the consolidation of new motor skills. Micro-consolidation was not modified by exercise.