Feedback-based Learning Research Articles

Feedback-based learning from viewpoints of surgical nursing students: A mixed-method study.

Feedback-based learning (FBL) focuses on guiding the learning process according to educational objectives and the student's needs. This study aimed to investigate surgical nursing students' perceptions and explore their experiences of FBL. The present study used a mixed-methods sequential explanatory design that was conducted in the quantitative and qualitative phases. Surgical nursing students participated in the quantitative phase (n = 105). In the first phase, students completed two questionnaires about FBL and clinical feedback. Semi-structured face-to-face interviews were used to collect qualitative data in the second phase. Graneheim and Lundman's inductive approaches were used to analyse the qualitative data. The mean (SD) score for students' perception of FBL was 3.99 ± 0.70. The qualitative results were explored in two themes, "motivational support for improvement" and "unpleasant learning". In this study, the positive and negative aspects of FBL were explained. FBL is perceived as a motivational support mechanism to improve students' capabilities during their academic courses and also prepare them for future careers. Conversely, FBL may experience unpleasant learning due to negative feedback and negative emotions.

The effect of feedback timing on category learning and feedback processing in younger and older adults.

Corrective feedback can be received immediately after an action or with a temporal delay. Neuroimaging studies suggest that immediate and delayed feedback are processed by the striatum and medial temporal lobes (MTL), respectively. Age-related changes in the striatum and MTL may influence the efficiency of feedback-based learning in older adults. The current study leverages event-related potentials (ERPs) to evaluate age-related differences in immediate and delayed feedback processing and consequences for learning. The feedback-related negativity (FRN) captures activity in the frontostriatal circuit while the N170 is hypothesized to reflect MTL activation. 18 younger (Myears = 24.4) and 20 older (Myears = 65.5) adults completed learning tasks with immediate and delayed feedback. For each group, learning outcomes and ERP magnitudes were evaluated across timing conditions. Younger adults learned better than older adults in the immediate timing condition. This performance difference was associated with a typical FRN signature in younger but not older adults. For older adults, impaired processing of immediate feedback in the striatum may have negatively impacted learning. Conversely, learning was comparable across groups when feedback was delayed. For both groups, delayed feedback was associated with a larger magnitude N170 relative to immediate feedback, suggesting greater MTL activation. Delaying feedback may increase MTL involvement and, for older adults, improve category learning. Age-related neural changes may differentially affect MTL- and striatal-dependent learning. Future research can evaluate the locus of age-related learning differences and how feedback can be manipulated to optimize learning across the lifespan.

Comparison of the effects of apprenticeship training by sandwich feedback and traditional methods on final-semester operating room technology students' perioperative competence and performance: a randomized, controlled trial.

Effective feedback is fundamental in clinical education, as it allows trainers to constantly diagnose the trainees' condition, determine their weaknesses, and intervene at proper times. Recently, different feedback-based approaches have been introduced in clinical training; however, the effectiveness of such interventions still needs to be studied extensively, especially in the perioperative field. Therefore, this study sought to compare the effects of apprenticeship training using sandwich feedback and traditional methods on the perioperative competence and performance of Operating Room (OR) technology students. Thirty final-semester undergraduate OR technology students taking the apprenticeship courses were randomly allocated into experimental (n = 15) and control (n = 15) groups through the stratified randomization approach. The students in the experimental group experienced Feedback-Based Learning (FBL) using a sandwich model, and the students in the control group participated in Traditional-Based Training (TBT) in six five-hour sessions weekly for three consecutive weeks. All students completed the Persian version of the Perceived Perioperative Competence Scale-Revised (PPCS-R) on the first and last days of interventions. Also, a blinded rater completed a checklist to evaluate all students' performance via Direct Observation of Procedural Skills (DOPS) on the last intervention day. Besides, the students in the FBL filled out a questionnaire regarding their attitude toward the implemented program. The mean total score of the PPCS-R was significantly higher in the FBL than in the TBT on the last intervention day (P < 0.001). Additionally, the increase in mean change of PPCS-R total score from the first to last days was significantly more in the FBL (P < 0.001). Likewise, the FBL students had higher DOPS scores than the TBT ones (P < 0.001). Most FBL students also had a good attitude toward the implemented program (n = 8; 53.3%). Apprenticeship training using a sandwich feedback-based approach was superior to the traditional method for enhancing perioperative competence and performance of final-semester OR technology students. Additional studies are required to identify the sustainability of the findings.

PELATIHAN PENGEMBANGAN MEDIA PEMBELAJARAN INOVATIF BERBASIS BAHAN SEDERHANA: TRANSFORMASI EVALUASI PEMBELAJARAN UNTUK GURU SDN 20 PANGKALPINANG

This training aims to provide knowledge and skills to teachers at SDN20 Pangkalpinang in developing innovative learning media based on simple materials and producing effective learning evaluations in the current era of technology. The methods used in this training include needs identification, training implementation, evaluation of learning outcomes, and monitoring and evaluation. Through this training, it is hoped that teachers can improve students' critical skills in Elementary School through the Feedback-Based Learning Model Based on the Socrative Application in the P5 Program. Needs identification is carried out through needs analysis and evaluation of teachers' learning evaluation practices, as an important initial step in designing a training program that meets their needs. This needs analysis provides a better understanding of the challenges faced by teachers in using innovative learning media based on simple materials and effective learning evaluation practices. The results of this training show an increase inknowledge and skills of teachers in developing innovative learning media and conducting learning evaluations. The training evaluation indicates that teachers feel more confident inimplementing new learning strategies and using technology in learning. Further monitoring and evaluation are needed to ensure the sustainability of implementing new learning strategies and the use of technology in learning.

One Size Does Not Fit All: Idiographic Computational Models Reveal Individual Differences in Learning and Meta-Learning Strategies.

Complex skill learning depends on the joint contribution of multiple interacting systems: working memory (WM), declarative long-term memory (LTM) and reinforcement learning (RL). The present study aims to understand individual differences in the relative contributions of these systems during learning. We built four idiographic, ACT-R models of performance on the stimulus-response learning, Reinforcement Learning Working Memory task. The task consisted of short 3-image, and long 6-image, feedback-based learning blocks. A no-feedback test phase was administered after learning, with an interfering task inserted between learning and test. Our four models included two single-mechanism RL and LTM models, and two integrated RL-LTM models: (a) RL-based meta-learning, which selects RL or LTM to learn based on recent success, and (b) a parameterized RL-LTM selection model at fixed proportions independent of learning success. Each model was the best fit for some proportion of our learners (LTM: 68.7%, RL: 4.8%, Meta-RL: 13.25%, bias-RL:13.25% of participants), suggesting fundamental differences in the way individuals deploy basic learning mechanisms, even for a simple stimulus-response task. Finally, long-term declarative memory seems to be the preferred learning strategy for this task regardless of block length (3- vs 6-image blocks), as determined by the large number of subjects whose learning characteristics were best captured by the LTM only model, and a preference for LTM over RL in both of our integrated-models, owing to the strength of our idiographic approach.

Retrieval-based inference in the acquired equivalence paradigm

IntroductionGeneralization is fundamental to cognition. In acquired equivalence, two stimuli that share a common association become treated as equivalent, with information acquired about one stimulus generalizing to the other. Acquired equivalence has been thought to rely on integrating related memories as they are encoded, resulting in fast spontaneous generalization, but other studies suggested effortful on-demand recombination of initially separate memories at retrieval. Here, we tested whether the tendency to separate vs. integrate related information may depend on a methodological detail of a traditional acquired equivalence paradigm.MethodsHuman participants underwent feedback-based learning of overlapping face-scene associations, choosing a correct scene for a face from two options on each trial. Foil (incorrect) scenes were controlled for half of the participants to ensure that they can only learn from corrective feedback. The other half had foils selected randomly on each trial, allowing statistical learning of face-scene co-occurrence to supplement feedback-based learning. We hypothesized that the opportunity for statistical learning would boost learning and generalization and facilitate memory integration.ResultsThe opportunity for statistical learning increased associative learning and generalization. However, rather than integrated memories, generalization was increased through learning during test.DiscussionThe results indicate that the tendency for generalization in the acquired equivalence is rather small, with no evidence for integrative encoding irrespective of group. The results inform current debates regarding encoding-based vs. retrieval-based mechanisms of generalization. They also highlight how methodological details may alter performance and the involvement of cognitive processes that underlie it.

The Role of the Human Cerebellum for Learning from and Processing of External Feedback in Non-Motor Learning: A Systematic Review

This review aimed to systematically identify and comprehensively review the role of the cerebellum in performance monitoring, focusing on learning from and on processing of external feedback in non-motor learning. While 1078 articles were screened for eligibility, ultimately 36 studies were included in which external feedback was delivered in cognitive tasks and which referenced the cerebellum. These included studies in patient populations with cerebellar damage and studies in healthy subjects applying neuroimaging. Learning performance in patients with different cerebellar diseases was heterogeneous, with only about half of all patients showing alterations. One patient study using EEG demonstrated that damage to the cerebellum was associated with altered neural processing of external feedback. Studies assessing brain activity with task-based fMRI or PET and one resting-state functional imaging study that investigated connectivity changes following feedback-based learning in healthy participants revealed involvement particularly of lateral and posterior cerebellar regions in processing of and learning from external feedback. Cerebellar involvement was found at different stages, e.g., during feedback anticipation and following the onset of the feedback stimuli, substantiating the cerebellum’s relevance for different aspects of performance monitoring such as feedback prediction. Future research will need to further elucidate precisely how, where, and when the cerebellum modulates the prediction and processing of external feedback information, which cerebellar subregions are particularly relevant, and to what extent cerebellar diseases alter these processes.

Declarative Learning Mechanisms Support Declarative but Not Probabilistic Feedback-Based Learning in Children with Developmental Language Disorder (DLD).

Declarative and probabilistic feedback-based learning was evaluated in 8-12-year-old school-age children with developmental language disorder (DLD; n = 14) and age-matched children with typical development (TD; n = 15). Children performed a visual two-choice word-learning task and a visual probabilistic classification task while their electroencephalogram (EEG) was recorded non-invasively from the scalp. Behavioral measures of accuracy and response to feedback, and electrophysiological responses to feedback were collected and compared between the two groups. While behavioral data indicated poorer performance by children with DLD in both learning paradigms, and similar response patterns to positive and negative feedback, electrophysiological data highlighted processing patterns in the DLD group that differed by task. More specifically, in this group, feedback processing in the context of declarative learning, which is known to be dominated by the medial temporal lobe (MTL), was associated with enhanced N170, an event-related brain potential (ERP) associated with MTL activation. The N170 amplitude was found to be correlated with declarative task performance in the DLD group. During probabilistic learning, known to be governed by the striatal-based learning system, the feedback-related negativity (FRN) ERP, which is the product of the cortico-striatal circuit dominated feedback processing. Within the context of probabilistic learning, enhanced N170 was associated with poor learning in the TD group, suggesting that MTL activation during probabilistic learning disrupts learning. These results are interpreted within the context of a proposed feedback parity hypothesis suggesting that in children with DLD, the system that dominates learning (i.e., MTL during declarative learning and the striatum during probabilistic learning) dominates and supports feedback processing.

DLSDHMS: Design of a deep learning-based analysis model for secure and distributed hospital management using context-aware sidechains

Designing an efficient hospital management solution requires the integration of multidomain operations that include secure storage, alert system modelling, infrastructure management, staff management, report analysis, and feedback-based learning tasks. Existing hospital management models are either highly complex or do not incorporate comprehensive deep learning analysis, which limits their deployment capabilities. Moreover, most of these models use mutable storage solutions, which restricts their trust levels under multi-patient to multi-doctor mapping scenarios. To overcome these issues, this article proposes the design of a novel deep Learning-based analysis model for secure and distributed hospital management via context-aware sidechains. The model initially collects large-scale information sets from different hospital entities via an IoT-based network and stores the information on context-sensitive sidechains. These context-sensitive sidechains store information sets related to Medicine Management, Doctor Management, Insurance and Billing Management, and Appointment Management operations. These chains are optimized via an Iterative Genetic Algorithm (IGA) that assists in improving storage and retrieval performance via intelligent merging and splitting operations. Information stored on these chains is processed via a combination of Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs), that assist in identifying patient-level diseases and issues. The information obtained from these classifiers is updated on the central repository and assists in the pre-emption of diseases for other patients. Due to these integrations, the proposed model is capable of reducing computational delay by 3.5 % and reducing storage cost by 8.3 % when compared to other blockchain-based deployments. The model is also able to pre-empt patient issues with 9.3 % higher accuracy and 4.8 % higher precision, which makes it useful for real-time clinical deployments.

An electrophysiological and behavioral investigation of feedback-based learning in aphasia

ABSTRACT Introduction Feedback is a fundamental aspect of aphasia treatments. However, learning from feedback is a cognitively demanding process. At the most basic level, individuals must detect feedback and extract outcome-related information (i.e., feedback processing). Neuroanatomical and neuropsychological differences associated with post-stroke aphasia may influence feedback processing and potentially how people with aphasia (PWA) respond to feedback-based treatments. To better understand how post-stroke aphasia affects feedback-based learning, the current study leverages event-related potentials (ERPs) to (1) characterize the relationship between feedback processing and learning, (2) identify cognitive skills that are associated with feedback processing, and (3) identify behavioural correlates of feedback-based learning in PWA. Methods Seventeen PWA completed a feedback-based novel word learning task. Feedback processing was measured using the feedback-related negativity (FRN), an ERP hypothesized to reflect the detection and evaluation of outcomes communicated via feedback. Individuals also completed neuropsychological assessments of language (phonological processing, verbal short-term memory) and executive functioning. Results PWA elicited an FRN that was sensitive to feedback valence. The magnitude of the FRN was not associated with novel word learning but was strongly correlated with performance on another feedback-based task, the Berg Card Sort. Cognitive variables (information updating, selective attention) but not language variables were associated with novel word learning. Discussion & Conclusion For PWA, feedback processing may be associated with learning in some but not all feedback-based contexts. These findings may inform future research in determining which variables moderate the relationship between feedback processing and learning with the long-term goal of identifying how feedback can be modified to support successful learning during aphasia rehabilitation.

Comparison between the Effects of Acute Physical and Psychosocial Stress on Feedback-Based Learning.

Stress modulates feedback-based learning, a process that has been implicated in declining mental function in aging and mental disorders. While acute physical and psychosocial stressors have been used interchangeably in studies on feedback-based learning, the two types of stressors involve distinct physiological and psychological processes. Whether the two types of stressors differentially influence feedback processing remains unclear. The present study compared the effects of physical and psychosocial stressors on feedback-based learning. Ninety-six subjects (Mage = 19.11 years; 50 female) completed either a cold pressor task (CPT) or mental arithmetic task (MAT), as the physical or psychosocial stressor, while electrocardiography and blood pressure were measured to assess cardiovascular stress reactivity (CVR). Self-ratings on the emotional valence of the stressors were also obtained. A probabilistic learning task was given prior to and after the stressors. Accuracy in selecting positive (Go accuracy) and avoiding negative stimuli (No-go accuracy) were recorded as learning outcomes. Repeated measures ANOVA and multiple regressions were used to compare the effects of two stressors and examine the effects of CVR and valence on the learning outcomes. The results showed that although the effects of CPT and MAT on feedback processing were not different, CVR and valence influenced Go and No-go accuracy, respectively. The results suggest that stress-modulated feedback-based learning involves multiple pathways and underscore the link between CVR and reward sensitivity. The findings have clinical implications and may contribute to a better understanding of human behavioral systems.

Altered learning and transfer abilities in Korsakoff’s syndrome depending on task complexity

Korsakoff’s syndrome (KS) is characterized by episodic memory impairment due to damage to the medial diencephalic structures. Although commonly associated with chronic alcoholism, starvation due to the hunger strike is one of its nonalcoholic causes. Learning the stimulus-response associations and transferring the just-learned associations to novel combinations were previously tested by specific tasks in memory-impaired patients with hippocampal, basal forebrain, and basal ganglia damage. To add to this previous research, we aimed to use the same tasks in a group of patients with hunger strike-related KS presenting a stable isolated amnestic profile. Twelve patients with hunger strike-related KS and matched healthy controls were tested in two tasks varying in task complexity. Each task included two phases: the initial phase is feedback-based learning of (simple vs. complex) stimulus-response associations, and the following phase is transfer generalization (in the presence vs. absence of feedback). On a task involving simple associations, five patients with KS failed to learn the associations, while the other seven patients showed intact learning and transfer. On the other task involving more complex associations, seven patients showed slower learning and failed at transfer generalization, whereas the other five patients failed even at the acquisition phase. These findings of a task-complexity-related impairment on associative learning and transfer represent a distinct pattern from the spared learning but impaired transfer previously observed on these tasks in patients with medial temporal lobe amnesia.

Cognition, body, and mind: A three-in-one coordinate-based fMRI meta-analysis on cognitive, physical, and meditative trainings.

While mounting evidence shows promising effects of brain training on cognitive functioning in healthy and pathological conditions, the spread of variable training approaches highlights the need to compare their efficacy and identify their neural correlates, representing possible targets for neuromodulation treatments. We performed coordinate-based functional magnetic resonance imaging meta-analyses to compare the neural correlates and the cognitive outcomes of cognitive (n = 22), physical (n = 22), and meditative (n = 20) training in healthy non-expert individuals. Pre/post-training cognitive metrics improved after cognitive and physical training, but their heterogeneity, or even the lack of these measurements in some studies, highlights the need of more structured protocols. Cognitive, physical, and meditative interventions increased brain activity in distinct fronto-medial areas likely mediating training effects on cognitive, action, and attentional control, respectively. The modular, training-specific, engagement of a region that is known to mediate feedback-based learning provides cues for boosting brain training via combined interventions that might jointly outperform their individual effects.

The contribution of theta and delta to feedback processing in children with developmental language disorder

PurposeThe study aimed at evaluating feedback processing at the electrophysiological level and its relation to learning in children with developmental language disorder (DLD) to further advance our understanding of the underlying neural mechanisms of feedback-based learning in children with this disorder.MethodA feedback-based probabilistic learning task required children to classify novel cartoon animals into two categories that differ on five binary features, the probabilistic combination of which determined classification. The learning outcomes’ variance in relation to time- and time–frequency measures of feedback processing were examined and compared between 20 children with developmental language disorder and 25 age-matched children with typical language development.ResultsChildren with developmental language disorder (DLD) performed poorer on the task when compared with their age-matched peers with typical language development (TD). The electrophysiological data in the time domain indicated no differences in the processing of positive and negative feedback among children with DLD. However, the time–frequency analysis revealed a strong theta activity in response to negative feedback in this group, suggesting an initial distinction between positive and negative feedback that was not captured by the ERP data. In the TD group, delta activity played a major role in shaping the FRN and P3a and was found to predict test performance. Delta did not contribute to the FRN and P3a in the DLD group. Additionally, theta and delta activities were not associated with the learning outcomes of children with DLD.ConclusionTheta activity, which is associated with the initial processing of feedback at the level of the anterior cingulate cortex, was detected in children with developmental language disorder (DLD) but was not associated with their learning outcomes. Delta activity, which is assumed to be generated by the striatum and to be linked to elaborate processing of outcomes and adjustment of future actions, contributed to processing and learning outcomes of children with typical language development but not of children with DLD. The results provide evidence for atypical striatum-based feedback processing in children with DLD.

Students’ perspective toward anonymous peer feedback in online writing classes

ABSTRACT Feedback in online learning is essential to improve both teaching and learning. In peer feedback, students discuss their work and the various problems they encounter in their writing. However, learners may not receive constructive feedback if their classmates have lower writing proficiency. Therefore, anonymous peer feedback training was applied in the writing class to improve the problem of peer feedback during the COVID-19 pandemic. This study first reviews the implementation of peer feedback, particularly with regard to challenges. Subsequently, it describes how anonymous peer feedback is implemented in writing courses. This study explores student attitudes toward anonymous peer feedback and their own ability to provide peer feedback. Meanwhile, it investigates the effect of anonymous peer feedback have on student writing proficiency in the EFL classroom. The 46 participants in this study comprised English department university undergraduates of differing seniority. They attended a weekly 2-hour writing course for a period of 18 weeks. During the experimental teaching, students who participated in anonymous peer feedback-based learning held more positive attitudes toward anonymous peer feedback. Finally, the study discusses student perceptions of anonymous peer feedback in writing courses.

Functional MRI study of feedback-based reinforcement learning in depression.

Reinforcement learning depends upon the integrity of emotional circuitry to establish associations between environmental cues, decisions, and positive or negative outcomes in order to guide behavior through experience. The emotional dysregulation characteristic of major depressive disorder (MDD) may alter activity in frontal and limbic structures that are key to learning. Although reward and decision-making have been examined in MDD, the effects of depression on associative learning is less well studied. We investigated whether depressive symptoms would be related to abnormalities in learning-related brain activity as measured by functional magnetic resonance imaging (fMRI). Also, we explored whether melancholic and atypical features were associated with altered brain activity. We conducted MRI scans on a 4T Varian MRI system in 10 individuals with MDD and 10 healthy subjects. We examined event-related brain activation during feedback-based learning task using Analysis of Functional NeuroImages (AFNI) for image processing and statistical analysis. We observed that MDD patients exhibited reduced activation in visual cortex but increased activation in cingulate and insular regions compared to healthy participants. Also, in relation to features of depressive subtypes, we observed that levels of activation in striatal, thalamic, and precuneus regions were negatively correlated with atypical characteristics. These results suggest that the effects of MDD change the neural circuitry underlying associative learning, and these effects may depend upon subtype features of MDD.

Altered functional connectivity during performance feedback processing in multiple sclerosis

Effective learning from performance feedback is vital for adaptive behavior regulation necessary for successful cognitive performance. Yet, how this learning operates in clinical groups that experience cognitive dysfunction is not well understood. Multiple sclerosis (MS) is an autoimmune, degenerative disease of the central nervous system characterized by physical and cognitive dysfunction. A highly prevalent impairment in MS is cognitive fatigue (CF). CF is associated with altered functioning within cortico-striatal regions that also facilitate feedback-based learning in neurotypical (NT) individuals. Despite this cortico-striatal overlap, research about feedback-based learning in MS, its associated neural underpinnings, and its sensitivity to CF, are all lacking. The present study investigated feedback-based learning ability in MS, as well as associated cortico-striatal function and connectivity. MS and NT participants completed a functional magnetic resonance imaging (fMRI) paired-word association task during which they received trial-by-trial monetary, non-monetary, and uninformative performance feedback. Despite reporting greater CF throughout the task, MS participants displayed comparable task performance to NTs, suggesting preserved feedback-based learning ability in the MS group. Both groups recruited the ventral striatum (VS), caudate nucleus, and ventromedial prefrontal cortex in response to the receipt of performance feedback, suggesting that people with MS also recruit cortico-striatal regions during feedback-based learning. However, compared to NT participants, MS participants also displayed stronger functional connectivity between the VS and task-relevant regions, including the left angular gyrus and right superior temporal gyrus, in response to feedback receipt. Results indicate that CF may not interfere with feedback-based learning in MS. Nonetheless, people with MS may recruit alternative connections with the striatum to assist with this form of learning. These findings have implications for cognitive rehabilitation treatments that incorporate performance feedback to remediate cognitive dysfunction in clinical populations.

Deepsign: Sign Language Detection and Recognition Using Deep Learning

The predominant means of communication is speech; however, there are persons whose speaking or hearing abilities are impaired. Communication presents a significant barrier for persons with such disabilities. The use of deep learning methods can help to reduce communication barriers. This paper proposes a deep learning-based model that detects and recognizes the words from a person’s gestures. Deep learning models, namely, LSTM and GRU (feedback-based learning models), are used to recognize signs from isolated Indian Sign Language (ISL) video frames. The four different sequential combinations of LSTM and GRU (as there are two layers of LSTM and two layers of GRU) were used with our own dataset, IISL2020. The proposed model, consisting of a single layer of LSTM followed by GRU, achieves around 97% accuracy over 11 different signs. This method may help persons who are unaware of sign language to communicate with persons whose speech or hearing is impaired.

Neuroevolution Guided Hybrid Spiking Neural Network Training.

Neuromorphic computing algorithms based on Spiking Neural Networks (SNNs) are evolving to be a disruptive technology driving machine learning research. The overarching goal of this work is to develop a structured algorithmic framework for SNN training that optimizes unique SNN-specific properties like neuron spiking threshold using neuroevolution as a feedback strategy. We provide extensive results for this hybrid bio-inspired training strategy and show that such a feedback-based learning approach leads to explainable neuromorphic systems that adapt to the specific underlying application. Our analysis reveals 53.8, 28.8, and 28.2% latency improvement for the neuroevolution-based SNN training strategy on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively in contrast to state-of-the-art conversion based approaches. The proposed algorithm can be easily extended to other application domains like image classification in presence of adversarial attacks where 43.2 and 27.9% latency improvements were observed on CIFAR-10 and CIFAR-100 datasets, respectively.

Cognitive Fatigue Alters Cortico-Striatal Functional Connectivity During Feedback-Based Learning in Multiple Sclerosis

Cognitive Fatigue Alters Cortico-Striatal Functional Connectivity During Feedback-Based Learning in Multiple Sclerosis