Training Tasks Research Articles

Multilevel Leapfrogging Initialization Strategy for Quantum Approximate Optimization Algorithm

AbstractRecently, Zhou et al. have proposed an Interpolation‐based (INTERP) strategy to generate the initial parameters for Quantum Approximate Optimization Algorithm (QAOA). INTERP guesses the initial parameters at level by applying interpolation to the optimized parameters at level , achieving better performance than random initialization (RI). Nevertheless, INTERP consumes extensive costs for deep QAOA because it necessitates optimization at each level depth. To address it, a Multilevel Leapfrogging Interpolation (MLI) strategy is proposed. MLI produces initial parameters from level to () at level , omitting the optimization rounds from level to . MLI executes optimization at few levels rather than each level, and this operation is called Multilevel Leapfrogging optimization (M‐Leap). The performance of MLI is investigated on the Maxcut problem. The simulation results demonstrate MLI achieves the same quasi‐optima as INTERP while consuming 1/2 of costs required by INTERP. Besides, for MLI, where there is no RI except for level 1, the greedy‐MLI strategy is presented. The simulation results suggest greedy‐MLI has better stability than INTERP and MLI beyond obtaining the quasi‐optima. According to the efficiency of finding the quasi‐optima, the idea of M‐Leap might be extended to other training tasks, especially those requiring numerous optimizations.

Virtual Reality Adaptive Training for Personalized Stress Inoculation.

To evaluate a personalized adaptive training program designed for stress prevention using graduated stress exposure. Astronauts in the high-risk space mission environment are prone to performance-impairing stress responses, making preemptive stress inoculation essential for their training. This work developed an adaptive virtual reality-based system that adjusts environmental stressors based on real-time stress indicators to optimize training stress levels. Sixty-five healthy subjects underwent task training in one of three groups: skill-only (no stressors), fixed-graduated (prescheduled stressor changes), and adaptive. Psychological (subjective stress, task engagement, distress, worry, anxiety, and workload) and physiological (heart rate, heart rate variability, blood pressure, and electrodermal activity) responses were measured. The adaptive condition showed a significant decrease in heart rate and a decreasing trend in heart rate variability ratio, with no changes in the other training conditions. Distress showed a decreasing trend for the graduated and adaptive conditions. Task engagement showed a significant increase for adaptive and a significant decrease for the graduated condition. All training conditions showed a significant decrease in worry and anxiety and a significant increase in the other heart rate variability metrics. Although all training conditions mitigated some stress, the preponderance of trial effects for the adaptive condition supports that it is more successful at decreasing stress. The integration of real-time personalized stress exposure within a VR-based training program not only prepares individuals for high-stress situations by preemptively mitigating stress but also customizes stressor levels to the crew member's current state, potentially enhancing resilience to future stressors.

Multi-head sequence tagging model for Grammatical Error Correction

To solve the Grammatical Error Correction (GEC) problem , a mapping between a source sequence and a target one is needed, where the two differ only on few spans. For this reason, the attention has been shifted to the non-autoregressive or sequence tagging models. In which, the GEC has been simplified from Seq2Seq to labeling the input tokens with edit commands chosen from a large edit space. Due to this large number of classes and the limitation of the available datasets, the current sequence tagging approaches still have some issues handling a broad range of grammatical errors just by being laser-focused on one single task. To this end, we simplified the GEC further by dividing it into seven related subtasks: Insertion, Deletion, Merge, Substitution, Transformation, Detection, and Correction, with Correction being our primary focus. A distinct classification head is dedicated to each of these subtasks. The novel multi-head and multi-task learning model is proposed to effectively utilize training data and harness the information from related task training signals. To mitigate the limited number of available training samples, a new denoising autoencoder is used to generate a new synthetic dataset to be used for pretraining. Additionally, a new character-level transformation is proposed to enhance the sequence-to-edit function and improve the model’s vocabulary coverage. Our single/ensemble model achieves an F0.5 of 74.4/77.0, and 68.6/69.1 on BEA-19 (test) and CoNLL-14 (test) respectively. Moreover, evaluated on JFLEG test set, the GLEU scores are 61.6 and 61.7 for the single and ensemble models, respectively. It mostly outperforms recently published state-of-the-art results by a considerable margin.

Neurochemical Predictors of Generalized Learning Induced by Brain Stimulation and Training.

Methods of cognitive enhancement for humans are most impactful when they generalize across tasks. However, the extent to which such "transfer" is possible via interventions is widely debated. In addition, the contribution of excitatory and inhibitory processes to such transfer is unknown. Here, in a large-scale neuroimaging individual differences study with humans (both sexes), we paired multitasking training and noninvasive brain stimulation (transcranial direct current stimulation, tDCS) over multiple days and assessed performance across a range of paradigms. In addition, we varied tDCS dosage (1.0 and 2.0 mA), electrode montage (left or right prefrontal regions), and training task (multitasking vs a control task) and assessed GABA and glutamate concentrations via ultrahigh field 7T magnetic resonance spectroscopy. Generalized benefits were observed in spatial attention, indexed by visual search performance, when multitasking training was combined with 1.0 mA stimulation targeting either the left or right prefrontal cortex (PFC). This transfer effect persisted for ∼30 d post intervention. Critically, the transferred benefits associated with right prefrontal tDCS were predicted by pretraining concentrations of glutamate in the PFC. Thus, the effects of this combined stimulation and training protocol appear to be linked predominantly to excitatory brain processes.

Theoretical Basis of Training of Pedagogues and Psychologists for the Development of Cognitive Activity of Teenagers

The main problem: the current directions of its development are determined in the article by conducting a theoretical analysis of philosophical, pedagogical, psychological, scientific and methodical works on the training of specialists for the development of the cognitive activity of teenagers. Currently, it is shown that the training of specialists in the development of cognitive activity of teenagers is a pedagogical and psychological problem. Purpose: to clarify the theory and propose a technology for the training of pedagogical and psychological specialists for the development of the cognitive activity of adolescents. Methods: When conducting the research, it was important to take into account statistical data that were sufficiently understandable and reliable. Therefore, in the framework of our research, we used the methodology of B. E. Milman, survey, method of expert evaluation, conversation, questionnaire, interview, series of tests, which include observation and open questions. The results and their significance: according to the results, the methodological predominance of the average level of social intelligence allowed students to see the following signs: the social significance of professional behavior, actions, relationships, full mastery of theoretical knowledge. During the course, we believe that the existence of a reflexive culture, which is evidenced by the improvement of communication in everyday life, in turn, is very valuable. Development of thinking, training and education of future teachers-psychologists, preparation for creative activity depend on methodological competence, qualifications and training of the teacher in the organization of research activities. Self-learning needs and skills do not arise by themselves. Such qualities begin to be formed in the process of organizing educational activities during the joint work of teachers and students in and out of class, even during school. In accordance with the tasks of the professional training of the future pedagogue-psychologist, active methods of training - problem-based lectures, seminars, debates and discussions, professional-oriented special courses, course and diploma works, scientific studies of school pedagogy and didactics, educational events such as scientifically organized forms of continuous pedagogical practice. As a result of mastering pedagogical activity, professional motivation of future pedagogical-psychological specialists is formed, understanding of goals and tasks, subject, psychological-pedagogical and didactic-methodical knowledge is developed, as well as relevant skills and abilities necessary for the development of cognitive activity of teenagers.

Генерация файлов формата Moodle XML на основе данных сбалансированного лингвистического корпуса

The aim of the proposed research is to develop an algorithm for generating educational (linguodidactic) content for popular learning management systems based on corpus data. The scientific novelty lies in the fact that for the first time, a linguodidactic component is added to the original author’s concept of the method for generating a balanced linguistic corpus, implemented on the general principles of maximum automation and universality of application. During the research, the structures of LMS Moodle backup files were studied, a software module was developed for converting data from the author’s balanced linguistic corpus with morphological markup into XML files, which were imported and tested for integrity and correctness in terms of solving the posed linguodidactic task. As a result, it was proved that the used linguistic corpus has a high linguodidactic potential, the created algorithm shows good results, in this case, for generating test or training tasks in German, and can be expanded to material from other languages, the support of which is provided by the software tool – the corpus generator.

Patient's Healthy-Limb Motion Characteristic-Based Assist-As-Needed Control Strategy for Upper-Limb Rehabilitation Robots.

The implementation of a progressive rehabilitation training model to promote patients' motivation efforts can greatly restore damaged central nervous system function in patients. Patients' active engagement can be effectively stimulated by assist-as-needed (AAN) robot rehabilitation training. However, its application in robotic therapy has been hindered by a simple determination method of robot-assisted torque which focuses on the evaluation of only the affected limb's movement ability. Moreover, the expected effect of assistance depends on the designer and deviates from the patient's expectations, and its applicability to different patients is deficient. In this study, we propose a control method with personalized treatment features based on the idea of estimating and mapping the stiffness of the patient's healthy limb. This control method comprises an interactive control module in the task-oriented space based on the quantitative evaluation of motion needs and an inner-loop position control module for the pneumatic swing cylinder in the joint space. An upper-limb endpoint stiffness estimation model was constructed, and a parameter identification algorithm was designed. The upper limb endpoint stiffness which characterizes the patient's ability to complete training movements was obtained by collecting surface electromyographic (sEMG) signals and human-robot interaction forces during patient movement. Then, the motor needs of the affected limb when completing the same movement were quantified based on the performance of the healthy limb. A stiffness-mapping algorithm was designed to dynamically adjust the rehabilitation training trajectory and auxiliary force of the robot based on the actual movement ability of the affected limb, achieving AAN control. Experimental studies were conducted on a self-developed pneumatic upper limb rehabilitation robot, and the results showed that the proposed AAN control method could effectively estimate the patient's movement needs and achieve progressive rehabilitation training. This rehabilitation training robot that simulates the movement characteristics of the patient's healthy limb drives the affected limb, making the intensity of the rehabilitation training task more in line with the patient's pre-morbid limb-use habits and also beneficial for the consistency of bilateral limb movements.

Generalized Planning in PDDL Domains with Pretrained Large Language Models

Recent work has considered whether large language models (LLMs) can function as planners: given a task, generate a plan. We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain. In particular, we consider PDDL domains and use GPT-4 to synthesize Python programs. We also consider (1) Chain-of-Thought (CoT) summarization, where the LLM is prompted to summarize the domain and propose a strategy in words before synthesizing the program; and (2) automated debugging, where the program is validated with respect to the training tasks, and in case of errors, the LLM is re-prompted with four types of feedback. We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines. Overall, we find that GPT-4 is a surprisingly powerful generalized planner. We also conclude that automated debugging is very important, that CoT summarization has non-uniform impact, that GPT-4 is far superior to GPT-3.5, and that just two training tasks are often sufficient for strong generalization.

Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations

Generalization and sample efficiency have been long-standing issues concerning reinforcement learning, and thus the field of Offline Meta-Reinforcement Learning (OMRL) has gained increasing attention due to its potential of solving a wide range of problems with static and limited offline data. Existing OMRL methods often assume sufficient training tasks and data coverage to apply contrastive learning to extract task representations. However, such assumptions are not applicable in several real-world applications and thus undermine the generalization ability of the representations. In this paper, we consider OMRL with two types of data limitations: limited training tasks and limited behavior diversity and propose a novel algorithm called GENTLE for learning generalizable task representations in the face of data limitations. GENTLE employs Task Auto-Encoder (TAE), which is an encoder-decoder architecture to extract the characteristics of the tasks. Unlike existing methods, TAE is optimized solely by reconstruction of the state transition and reward, which captures the generative structure of the task models and produces generalizable representations when training tasks are limited. To alleviate the effect of limited behavior diversity, we consistently construct pseudo-transitions to align the data distribution used to train TAE with the data distribution encountered during testing. Empirically, GENTLE significantly outperforms existing OMRL methods on both in-distribution tasks and out-of-distribution tasks across both the given-context protocol and the one-shot protocol.

Incorporating Serverless Computing into P2P Networks for ML Training: In-Database Tasks and Their Scalability Implications (Student Abstract)

Distributed ML addresses challenges from increasing data and model complexities. Peer to peer (P2P) networks in distributed ML offer scalability and fault tolerance. However, they also encounter challenges related to resource consumption, and communication overhead as the number of participating peers grows. This research introduces a novel architecture that combines serverless computing with P2P networks for distributed training. Serverless computing enhances this model with parallel processing and cost effective scalability, suitable for resource-intensive tasks. Preliminary results show that peers can offload expensive computational tasks to serverless platforms. However, their inherent statelessness necessitates strong communication methods, suggesting a pivotal role for databases. To this end, we have enhanced an in memory database to support ML training tasks.

Fine-Grained Knowledge Selection and Restoration for Non-exemplar Class Incremental Learning

Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting since all techniques can only be applied to current task data. Considering this challenge, we propose a novel framework of fine-grained knowledge selection and restoration. The conventional knowledge distillation-based methods place too strict constraints on the network parameters and features to prevent forgetting, which limits the training of new tasks. To loose this constraint, we proposed a novel fine-grained selective patch-level distillation to adaptively balance plasticity and stability. Some task-agnostic patches can be used to preserve the decision boundary of the old task. While some patches containing the important foreground are favorable for learning the new task. Moreover, we employ a task-agnostic mechanism to generate more realistic prototypes of old tasks with the current task sample for reducing classifier bias for fine-grained knowledge restoration. Extensive experiments on CIFAR100, TinyImageNet and ImageNet-Subset demonstrate the effectiveness of our method. Code is available at https://github.com/scok30/vit-cil.

Neural Reasoning about Agents’ Goals, Preferences, and Actions

We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks - with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.

TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling

Task-oriented dialog systems have witnessed substantial progress due to conversational pre-training techniques. Yet, two significant challenges persist. First, most systems primarily utilize the latest turn's state label for the generator. This practice overlooks the comprehensive value of state labels in boosting the model's understanding for future generations. Second, an overreliance on generated policy often leads to error accumulation, resulting in suboptimal responses when adhering to incorrect actions. To combat these challenges, we propose turn-level multi-task objectives for the encoder. With the guidance of essential information from labeled intermediate states, we establish a more robust representation for both understanding and generation. For the decoder, we introduce an action tree-based scheduled sampling technique. Specifically, we model the hierarchical policy as trees and utilize the similarity between trees to sample negative policy based on scheduled sampling, hoping the model to generate invariant responses under perturbations. This method simulates potential pitfalls by sampling similar negative policy, bridging the gap between task-oriented dialog training and inference. Among methods without continual pre-training, our approach achieved state-of-the-art (SOTA) performance on the MultiWOZ dataset series and was also competitive with pre-trained SOTA methods.

ExpeL: LLM Agents Are Experiential Learners

The recent surge in research interest in applying large language models (LLMs) to decision-making tasks has flourished by leveraging the extensive world knowledge embedded in LLMs. While there is a growing demand to tailor LLMs for custom decision-making tasks, finetuning them for specific tasks is resource-intensive and may diminish the model's generalization capabilities. Moreover, state-of-the-art language models like GPT-4 and Claude are primarily accessible through API calls, with their parametric weights remaining proprietary and unavailable to the public. This scenario emphasizes the growing need for new methodologies that allow learning from agent experiences without requiring parametric updates. To address these problems, we introduce the Experiential Learning (ExpeL) agent. Our agent autonomously gathers experiences and extracts knowledge using natural language from a collection of training tasks. At inference, the agent recalls its extracted insights and past experiences to make informed decisions. Our empirical results highlight the robust learning efficacy of the ExpeL agent, indicating a consistent enhancement in its performance as it accumulates experiences. We further explore the emerging capabilities and transfer learning potential of the ExpeL agent through qualitative observations and additional experiments.

Towards Making Learnware Specification and Market Evolvable

The learnware paradigm aims to establish a market of numerous well-performed machine learning models, enabling users to leverage existing helpful models for their tasks instead of starting from scratch. Each learnware in the market is a model submitted by its developer, associated with a specification generated with the help of learnware market, representing the model's specialty and utility and enabling it to be identified for new user tasks. As the market continuously scales up, accommodating an ever-increasing number of learnwares, the critical challenge of the learnware paradigm is to effectively and efficiently identify the most helpful learnware(s) for a new user task without accessing the user's raw data. In this paper, to achieve increasingly accurate learnware characterization and identification along with a growing number of learnwares in the market, we propose an approach called Evolvable Learnware Specification with Index (ELSI). Specifically, based on the key idea of leveraging the task information within learnware specifications, we tackle the challenge of ascertaining the capabilities of models beyond their original training tasks, thereby enabling learnware specifications and the entire market to evolve continuously. Furthermore, through organizing learnwares and constructing specification indexes, we design a practical procedure to accurately and efficiently identify helpful learnwares without examining the entire market. Theoretical analysis and extensive experiments on a learnware market prototype encompassing thousands of models and covering six real-world scenarios validate the effectiveness and efficiency of our approach.

MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components

Meta-Reinforcement Learning (Meta-RL) aims to reveal shared characteristics in dynamics and reward functions across diverse training tasks. This objective is achieved by meta-learning a policy that is conditioned on task representations with encoded trajectory data or context, thus allowing rapid adaptation to new tasks from a known task distribution. However, since the trajectory data generated by the policy may be biased, the task inference module tends to form spurious correlations between trajectory data and specific tasks, thereby leading to poor adaptation to new tasks. To address this issue, we propose the Meta-RL with task unCertAinty feedback through decoupled context-aware Reward and Dynamics components (MetaCARD). MetaCARD distinctly decouples the dynamics and rewards when inferring tasks and integrates task uncertainty feedback from policy evaluation into the task inference module. This design effectively reduces uncertainty in tasks with changes in dynamics or/and reward functions, thereby enabling accurate task identification and adaptation. The experiment results on both Meta-World and classical MuJoCo benchmarks show that MetaCARD significantly outperforms prevailing Meta-RL baselines, demonstrating its remarkable adaptation ability in sophisticated environments that involve changes in both reward functions and dynamics.

Focus-Then-Decide: Segmentation-Assisted Reinforcement Learning

Visual Reinforcement Learning (RL) is a promising approach to achieve human-like intelligence. However, it currently faces challenges in learning efficiently within noisy environments. In contrast, humans can quickly identify task-relevant objects in distraction-filled surroundings by applying previously acquired common knowledge. Recently, foundational models in natural language processing and computer vision have achieved remarkable successes, and the common knowledge within these models can significantly benefit downstream task training. Inspired by these achievements, we aim to incorporate common knowledge from foundational models into visual RL. We propose a novel Focus-Then-Decide (FTD) framework, allowing the agent to make decisions based solely on task-relevant objects. To achieve this, we introduce an attention mechanism to select task-relevant objects from the object set returned by a foundational segmentation model, and only use the task-relevant objects for the subsequent training of the decision module. Additionally, we specifically employed two generic self-supervised objectives to facilitate the rapid learning of this attention mechanism. Experimental results on challenging tasks based on DeepMind Control Suite and Franka Emika Robotics demonstrate that our method can quickly and accurately pinpoint objects of interest in noisy environments. Consequently, it achieves a significant performance improvement over current state-of-the-art algorithms. Project Page: https://www.lamda.nju.edu.cn/chenc/FTD.html Code: https://github.com/LAMDA-RL/FTD

The structure of methodical competence of a physical education teacher

The article reveals the theoretical foundations of the development of methodological competence of future physical education teachers during their studies at higher education institutions. The essence and structure of the concept of ”methodical competence of a physical education teacher” was identified as one of the factors of proficiency which provides the teacher with knowledge, abilities and skills of organizing physical education and health activities, health methods and technologies for providing students with motor activity, skills and conducting the educational process on the subject “Physical education”. The purpose of the article is to study the structure of the methodical competence of the physical education teacher and to establish the components that must be developed during the training of students. The analysis of scientific and methodical literature shows a large number of different approaches to determining the structure of a teacher's methodical competence. We have identified the following structural components of the physical education teacher's methodological competence: motivational-targeted, organizational-contentual, procedural-active, reflective-creative. To ensure the development of each of the components of the methodological competence of the future physical education teacher, it is necessary to: 1) to create scientifically based planning of the educational process consisting of mandatory and optional educational components at the higher education institution; 2) to ensure unity and interconnection of theoretical, methodical and practical training of students; 3) to create a high but accessible level of difficulty in training classes, quick and high- quality mastery of the technique of performing exercises and mastering the method of their improvement; 4) to create maximum activity and independence of the students during classes; 5) to combine individual and collective physical culture and health activities of the students; 6) ensure the educational process with a sufficient quantity and quality of technical and sports equipment; 7) to ensure wide use of innovative technologies of physical culture, health and sports activities. The methodical competence of a physical education teacher depends on his professional preparation while studying at a higher education institution, namely: methodical, professional-pedagogical, psychological-pedagogical knowledge as well as knowledge in the fields of physical culture, health and sports, abilities and skills, motivational and valuable attitude towards his profession. The uniqueness of the methodical competence of a physical education teacher is determined by the specifics of solving training, educational and health-improving tasks regarding the formation of physical, psychological, spiritual and social health of student youth.

A Training Program Using Modified Joystick-Operated Ride-on Toys to Complement Conventional Upper Extremity Rehabilitation in Children with Cerebral Palsy: Results from a Pilot Study.

The pilot study assessed the utility of a training program using modified, commercially available dual-joystick-operated ride-on toys to promote unimanual and bimanual upper extremity (UE) function in children with cerebral palsy (CP). The ride-on-toy training was integrated within a 3-week, intensive, task-oriented training camp for children with CP. Eleven children with hemiplegia between 4 and 10 years received the ride-on-toy training program 20-30 min/day, 5 days/week for 3 weeks. Unimanual motor function was assessed using the Quality of Upper Extremity Skills Test (QUEST) before and after the camp. During ride-on-toy training sessions, children wore activity monitors on both wrists to assess the duration and intensity of bimanual UE activity. Video data from early and late sessions were coded for bimanual UE use, independent navigation, and movement bouts. Children improved their total and subscale QUEST scores from pretest to post-test while increasing moderate activity in their affected UE from early to late sessions, demonstrating more equal use of both UEs across sessions. There were no significant changes in the rates of movement bouts from early to late sessions. We can conclude that joystick-operated ride-on toys function as child-friendly, intrinsically rewarding tools that can complement conventional therapy and promote bimanual motor functions in children with CP.

Remote Evaluation of Sleep and Circadian Rhythms in Older Adults With Mild Cognitive Impairment and Dementia: Protocol for a Feasibility and Acceptability Mixed Methods Study.

Sleep disturbances are a potentially modifiable risk factor for neurodegenerative dementia secondary to Alzheimer disease (AD) and Lewy body disease (LBD). Therefore, we need to identify the best methods to study sleep in this population. This study will assess the feasibility and acceptability of various wearable devices, smart devices, and remote study tasks in sleep and cognition research for people with AD and LBD. We will deliver a feasibility and acceptability study alongside a prospective observational cohort study assessing sleep and cognition longitudinally in the home environment. Adults aged older than 50 years who were diagnosed with mild to moderate dementia or mild cognitive impairment (MCI) due to probable AD or LBD and age-matched controls will be eligible. Exclusion criteria include lack of capacity to consent to research, other causes of MCI or dementia, and clinically significant sleep disorders. Participants will complete a cognitive assessment and questionnaires with a researcher and receive training and instructions for at-home study tasks across 8 weeks. At-home study tasks include remote sleep assessments using wearable devices (electroencephalography headband and actigraphy watch), app-based sleep diaries, online cognitive assessments, and saliva samples for melatonin- and cortisol-derived circadian markers. Feasibility outcomes will be assessed relating to recruitment and retention, data completeness, data quality, and support required. Feedback on acceptability and usability will be collected throughout the study period and end-of-study interviews will be analyzed using thematic analysis. Recruitment started in February 2022. Data collection is ongoing, with final data expected in February 2024 and data analysis and publication of findings scheduled for the summer of 2024. This study will allow us to assess if remote testing using smart devices and wearable technology is a viable alternative to traditional sleep measurements, such as polysomnography and questionnaires, in older adults with and without MCI or dementia due to AD or LBD. Understanding participant experience and the barriers and facilitators to technology use for research purposes and remote research in this population will assist with the development of, recruitment to, and retention within future research projects studying sleep and cognition outside of the clinic or laboratory. DERR1-10.2196/52652.