Learning Task Research Articles

Lesions to the mediodorsal thalamus, but not orbitofrontal cortex, enhance volatility beliefs linked to paranoia

Beliefs-attitudes toward some state of the environment-guide action selection and should be robust to variability but sensitive to meaningful change. Beliefs about volatility (expectation of change) are associated with paranoia in humans, but the brain regions responsible for volatility beliefs remain unknown. The orbitofrontal cortex (OFC) is central to adaptive behavior, whereas the magnocellular mediodorsal thalamus (MDmc) is essential for arbitrating between perceptions and action policies. We assessed belief updating in a three-choice probabilistic reversal learning task following excitotoxic lesions of the MDmc (n = 3) or OFC (n= 3) and compared performance with that of unoperated monkeys (n= 14). Computational analyses indicated a double dissociation: MDmc, but not OFC, lesions were associated with erratic switching behavior and heightened volatility belief (as in paranoia in humans), whereas OFC, but not MDmc, lesions were associated with increased lose-stay behavior and reward learning rates. Given the consilience across species and models, these results have implications for understanding paranoia.

Effectiveness Study of Machine Learning Task of Detection Hands Position by Keypoints

Effectiveness Study of Machine Learning Task of Detection Hands Position by Keypoints

Deep Neural Networks and Tabular Data: A Survey.

Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous datasets, deep neural networks have repeatedly shown excellent performance and have therefore been widely adopted. However, their adaptation to tabular data for inference or data generation tasks remains highly challenging. To facilitate further progress in the field, this work provides an overview of state-of-the-art deep learning methods for tabular data. We categorize these methods into three groups: data transformations, specialized architectures, and regularization models. For each of these groups, our work offers a comprehensive overview of the main approaches. Moreover, we discuss deep learning approaches for generating tabular data and also provide an overview over strategies for explaining deep models on tabular data. Thus, our first contribution is to address the main research streams and existing methodologies in the mentioned areas while highlighting relevant challenges and open research questions. Our second contribution is to provide an empirical comparison of traditional machine learning methods with 11 deep learning approaches across five popular real-world tabular datasets of different sizes and with different learning objectives. Our results, which we have made publicly available as competitive benchmarks, indicate that algorithms based on gradient-boosted tree ensembles still mostly outperform deep learning models on supervised learning tasks, suggesting that the research progress on competitive deep learning models for tabular data is stagnating. To the best of our knowledge, this is the first in-depth overview of deep learning approaches for tabular data; as such, this work can serve as a valuable starting point to guide researchers and practitioners interested in deep learning with tabular data.

Partial Tubal Nuclear Norm-Regularized Multiview Subspace Learning.

In this article, a unified multiview subspace learning model, called partial tubal nuclear norm-regularized multiview subspace learning (PTN2MSL), was proposed for unsupervised multiview subspace clustering (MVSC), semisupervised MVSC, and multiview dimension reduction. Unlike most of the existing methods which treat the above three related tasks independently, PTN2MSL integrates the projection learning and the low-rank tensor representation to promote each other and mine their underlying correlations. Moreover, instead of minimizing the tensor nuclear norm which treats all singular values equally and neglects their differences, PTN2MSL develops the partial tubal nuclear norm (PTNN) as a better alternative solution by minimizing the partial sum of tubal singular values. The PTN2MSL method was applied to the above three multiview subspace learning tasks. It demonstrated that these tasks organically benefited from each other and PTN2MSL has achieved better performance in comparison to state-of-the-art methods.

From land to water: “Sunken” T-maze for associated learning in cichlid fish

The study introduced and evaluated learning paradigms for Maylandia callainos cichlids using a modified version of the rodent T-maze, filled with tank water (the "sunken" modification). Both male and female fish underwent training in two distinct conditioning paradigms. Firstly, simple operant conditioning involved placing a food reward in either the right or left compartment. Cichlids demonstrated the ability to purposefully find the bait within 6 days of training, with a persistent place preference lasting up to 6 days. Additionally, the learning dynamics varied with sex: female cichlids exhibited reduction in latency to visit the target compartment and consume the bait, along with a decrease in the number of errors 3 and 4 days earlier than males, respectively. Secondly, visually-cued operant conditioning was conducted, with a food reward exclusively placed in the yellow compartment, randomly positioned on the left or right side of the maze during each training session. Visual learning persisted for 10 days until reaction time improvement plateaued. Color preference disappeared after 4 consecutive check-ups, with no sex-related interference. For further validation of visually-cued operant conditioning paradigm, drugs MK-801 (dizocilpine) and caffeine, known to affect performance in learning tasks, were administered intraperitoneally. Chronic MK-801 (0.17 mg/kg) impaired maze learning, resulting in no color preference development. Conversely, caffeine administration enhanced test performance, increasing precision in fish. This developed paradigm offers a viable approach for studying learning and memory and presents an effective alternative to rodent-based drug screening tools, exhibiting good face and predictive validity.

Bagaimana Hubungan antara Belief in Math dan Metode Project Based Learning dalam Pembelajaran Matematika?

Belief in math is a students' attitudes toward mathematics, where students can give a positive or negative response to the mathematics learning activities. Students are given a math problem and when complete it, they will think first, then by the time students are expected to make sure the answer and concepts used are appropriate. Any given cultivated mathematical problems always follow the real-world context in which the students participate actively and creatively. The task of project-based learning that given by the teacher to the students is one of some ways to solve the problem and make the students understand on their own way. This method was literature review that used to find out the relationship between student belief in math and learning mathematics using project based learning method. The relationship between belief in in math and project based learning is in their project learning that consists of several steps on their application aims to help students further develop, not only in knowledge but also belief in math student as the passage of the process of the project, students will be challenge theirself and trust to himself to completing their own projects.

Lyapunov-guided deep reinforcement learning for delay-aware online task offloading in MEC systems

With the arrival of 5G technology and the popularization of the Internet of Things (IoT), mobile edge computing (MEC) has great potential in handling delay-sensitive and compute-intensive (DSCI) applications. Meanwhile, the need for reduced latency and improved energy efficiency in terminal devices is becoming urgent increasingly. However, the users are affected by channel conditions and bursty computational demands in dynamic MEC environments, which can lead to longer task correspondence times. Therefore, finding an efficient task offloading method in stochastic systems is crucial for optimizing system energy consumption. Additionally, the delay due to frequent user–MEC interactions cannot be overlooked. In this article, we initially frame the task offloading issue as a dynamic optimization issue. The goal is to minimize the system’s long-term energy consumption while ensuring the task queue’s stability over the long term. Using the Lyapunov optimization technique, the task processing deadline problem is converted into a stability control problem for the virtual queue. Then, a novel Lyapunov-guided deep reinforcement learning (DRL) for delay-aware offloading algorithm (LyD2OA) is designed. LyD2OA can figure out the task offloading scheme online, and adaptively offload the task with better network quality. Meanwhile, it ensures that deadlines are not violated when offloading tasks in poor communication environments. In addition, we perform a rigorous mathematical analysis of the performance of Ly2DOA and prove the existence of upper bounds on the virtual queue. It is theoretically proven that LyD2OA enables the system to realize the trade-off between energy consumption and delay. Finally, extensive simulation experiments verify that LyD2OA has good performance in minimizing energy consumption and keeping latency low.

Early-Stage Alzheimer's Disease Affects Fast But Not Slow Adaptive Processes in Motor Learning.

Alzheimer's disease (AD) is characterized by an initial decline in declarative memory, while nondeclarative memory processing remains relatively intact. Error-based motor adaptation is traditionally seen as a form of nondeclarative memory, but recent findings suggest that it involves both fast, declarative, and slow, nondeclarative adaptive processes. If the declarative memory system shares resources with the fast process in motor adaptation, it can be hypothesized that the fast, but not the slow, process is disturbed in AD patients. To test this, we studied 20 early-stage AD patients and 21 age-matched controls of both sexes using a reach adaptation paradigm that relies on spontaneous recovery after sequential exposure to opposing force fields. Adaptation was measured using error clamps and expressed as an adaptation index (AI). Although patients with AD showed slightly lower adaptation to the force field than the controls, both groups demonstrated effects of spontaneous recovery. The time course of the AI was fitted by a hierarchical Bayesian two-state model in which each dynamic state is characterized by a retention and learning rate. Compared to controls, the retention rate of the fast process was the only parameter that was significantly different (lower) in the AD patients, confirming that the memory of the declarative, fast process is disturbed by AD. The slow adaptive process was virtually unaffected. Since the slow process learns only weakly from an error, our results provide neurocomputational evidence for the clinical practice of errorless learning of everyday tasks in people with dementia.

과업 유형이 고등학교 영어 학습자의 동사 하위범주화 자질 학습에 미치는 영향

Purpose: This study investigated the influence of task involvement levels on Korean high school students' learning of verb subcategorization knowledge. Based on the Task-induced involvement load hypothesis in vocabulary acquisition, we analyzed whether different tasks with varying levels of involvement affect the learning of sentence structures inevitably derived from verbs. Methods: Sixty homogeneous Korean second-year high school students were selected and were divided into three groups, for applying different types of tasks. We used nine verbs belonging to the “putting verb” category, and different levels of task involvement were presented to each group. Pre- and post-tests were conducted to assess the students' knowledge of verb subcategorization. Results: The results indicated that there was no statistically significant difference between task involvement levels and learning of verb subcategorization. Furthermore, a discrepancy was observed between the proficiency levels determined by the national English test and the knowledge of verb subcategorization. Conclusion: The distinction in task involvement did not significantly affect the learning of the subcategorization features of verbs. However, given the disparity between knowledge of verb subcategorization features and nationwide English proficiency assessment results, it is proposed that there is a need for English education to develop proficiency in verbal communication skills.

Astrocytes as a mechanism for contextually-guided network dynamics and function.

Astrocytes are a ubiquitous and enigmatic type of non-neuronal cell and are found in the brain of all vertebrates. While traditionally viewed as being supportive of neurons, it is increasingly recognized that astrocytes play a more direct and active role in brain function and neural computation. On account of their sensitivity to a host of physiological covariates and ability to modulate neuronal activity and connectivity on slower time scales, astrocytes may be particularly well poised to modulate the dynamics of neural circuits in functionally salient ways. In the current paper, we seek to capture these features via actionable abstractions within computational models of neuron-astrocyte interaction. Specifically, we engage how nested feedback loops of neuron-astrocyte interaction, acting over separated time-scales, may endow astrocytes with the capability to enable learning in context-dependent settings, where fluctuations in task parameters may occur much more slowly than within-task requirements. We pose a general model of neuron-synapse-astrocyte interaction and use formal analysis to characterize how astrocytic modulation may constitute a form of meta-plasticity, altering the ways in which synapses and neurons adapt as a function of time. We then embed this model in a bandit-based reinforcement learning task environment, and show how the presence of time-scale separated astrocytic modulation enables learning over multiple fluctuating contexts. Indeed, these networks learn far more reliably compared to dynamically homogeneous networks and conventional non-network-based bandit algorithms. Our results fuel the notion that neuron-astrocyte interactions in the brain benefit learning over different time-scales and the conveyance of task-relevant contextual information onto circuit dynamics.

Designs of graph echo state networks for node classification

Among the Graph Neural Network (GNN) models that address the task of node classification, Graph Echo State Networks (GESN) have proved particularly effective in addressing the challenge of heterophily, i.e. the presence of a significant fraction of inter-class edges in the learning task graph. The effectiveness of GESN is paired with its efficiency, owing to the reservoir computing paradigm. While previous literature has analyzed the design of reservoirs for sequence ESN and GESN for graph-level tasks, the problem of providing effective designs of reservoirs for node-level GESN is so far largely unexplored. In this paper we analyze the impact of different reservoir designs on node classification accuracy and on the quality of node embeddings computed by GESN, focusing both on dense and sparse reservoir layouts. As measures of embedding richness, we adopt both graph topology-dependent metrics previously employed in the analysis of embedding smoothing, and topology-independent metrics from the areas of information theory and numerical analysis. In particular, we propose the application of entropy measures for quantifying information in node embeddings.

Few-shot image classification via hybrid representation

Few-shot image classification aims to learn an embedding model on the base datasets and design a base learner to recognize novel categories. The few-shot image classification framework is a two-phase process. First, the pre-train phase utilizes the base data to train a CNN-based feature extractor. Next, in the meta-test phase, the frozen feature extractor is applied to novel data with categories different from the base data. A base learner is then designed for recognition. Several simple base learners, including nearest neighbor, support vector machine, and logistic regression classifiers, have been recently introduced for few-shot learning tasks. However, these base learners are separately designed to consider specific representations (e.g., the class center) or shared representations (e.g., the boundaries). This paper mainly focuses on exploring the representation-residual base learners, which aim to represent a query sample with the support set and predict the query sample’s label based on the minimal residual error. We first introduce two representation-residual base learners: a specific representation base learner and a shared representation base learner. Then, we propose a novel hybrid representation base learner that combines both base learners to generate competitive representation. Additionally, we extend our approach by incorporating a self-training framework to utilize the query data fully. We evaluate our proposed method on several benchmark few-shot image classification datasets, such as miniImageNet, tieredImageNet, CIFAR-FS, FC100, and CUB datasets. The experimental results indicate that our proposed approach shows a significant performance improvement.

Self-supervised Learning for Speech Emotion Recognition Task Using Audio-visual Features and Distil Hubert Model on BAVED and RAVDESS Databases

Self-supervised Learning for Speech Emotion Recognition Task Using Audio-visual Features and Distil Hubert Model on BAVED and RAVDESS Databases

Toddlers' prior social experience with speakers influences their word learning.

Toddlers prefer to learn from familiar adults, particularly their caregivers, and perform better on word learning tasks when taught by caregivers than by strangers. However, it remains unclear why toddlers learn better from caregivers than from strangers. One possibility is that toddlers are more receptive to learning from individuals whom they have found to be engaging in previous interactions. The current study tested whether toddlers learn more from an unfamiliar adult who was previously engaging than from an unfamiliar adult who was previously unengaging. Toddlers (27-29months, N=40) were taught labels for novel objects by two different experimenters. Prior to word learning, toddlers watched pre-recorded videos of one experimenter utilizing engaging behaviors (i.e., using infant-directed speech, gestures, eye contact, and positive affect) and one experimenter utilizing unengaging behaviors (i.e., using adult-directed speech, no gestures, no eye contact, and neutral affect). Both experimenters were equally engaging during labeling. Word learning was then tested using a looking-while-listening paradigm. The results of linear mixed-effects model, cluster-based permutation, and growth curve analyses suggest heightened performance for words that were taught by the experimenter who was previously engaging. These results begin to reveal the kinds of social experiences that promote success in early word learning.

Task-Specific Rapid Auditory Perceptual Learning in Adult Cochlear Implant Recipients: What Could It Mean for Speech Recognition.

Speech recognition in cochlear implant (CI) recipients is quite variable, particularly in challenging listening conditions. Demographic, audiological, and cognitive factors explain some, but not all, of this variance. The literature suggests that rapid auditory perceptual learning explains unique variance in speech recognition in listeners with normal hearing and those with hearing loss. The present study focuses on the early adaptation phase of task-specific rapid auditory perceptual learning. It investigates whether adult CI recipients exhibit this learning and, if so, whether it accounts for portions of the variance in their recognition of fast speech and speech in noise. Thirty-six adult CI recipients (ages = 35 to 77, M = 55) completed a battery of general speech recognition tests (sentences in speech-shaped noise, four-talker babble noise, and natural-fast speech), cognitive measures (vocabulary, working memory, attention, and verbal processing speed), and a rapid auditory perceptual learning task with time-compressed speech. Accuracy in the general speech recognition tasks was modeled with a series of generalized mixed models that accounted for demographic, audiological, and cognitive factors before accounting for the contribution of task-specific rapid auditory perceptual learning of time-compressed speech. Most CI recipients exhibited early task-specific rapid auditory perceptual learning of time-compressed speech within the course of the first 20 sentences. This early task-specific rapid auditory perceptual learning had unique contribution to the recognition of natural-fast speech in quiet and speech in noise, although the contribution to natural-fast speech may reflect the rapid learning that occurred in this task. When accounting for demographic and cognitive characteristics, an increase of 1 SD in the early task-specific rapid auditory perceptual learning rate was associated with ~52% increase in the odds of correctly recognizing natural-fast speech in quiet, and ~19% to 28% in the odds of correctly recognizing the different types of speech in noise. Age, vocabulary, attention, and verbal processing speed also had unique contributions to general speech recognition. However, their contribution varied between the different general speech recognition tests. Consistent with previous findings in other populations, in CI recipients, early task-specific rapid auditory perceptual, learning also accounts for some of the individual differences in the recognition of speech in noise and natural-fast speech in quiet. Thus, across populations, the early rapid adaptation phase of task-specific rapid auditory perceptual learning might serve as a skill that supports speech recognition in various adverse conditions. In CI users, the ability to rapidly adapt to ongoing acoustical challenges may be one of the factors associated with good CI outcomes. Overall, CI recipients with higher cognitive resources and faster rapid learning rates had better speech recognition.

PSVMLP: Point and Shifted Voxel MLP for 3D deep learning

We propose a high-performance 3D feature extraction deep learning network based on point cloud and shifted voxel, named Point and Shifted Voxel MLP (PSVMLP). The main component of PSVMLP is simple Multi-Layer Perceptron (MLP) structure. PSVMLP achieves effective extraction of multi-scale features from 3D data. Specifically, we combine point cloud and voxel-based feature extraction methods. In voxel representation learning, we propose a wide-range geometric feature extraction method based on axial shifting operations and simple MLP structure. The axial shifting operations allow shifting voxels in the depth, height, and width directions, capturing more geometric information. In point cloud representation learning, we use simple MLP structure to extract local features, and we also extract global features by combining transformer structure. By combining point cloud and voxel feature extraction methods, we obtain rich feature representations from different scales, enhancing the model’s expressive power and generalization performance. Applying our designed model to basic geometric feature learning tasks, we achieve excellent results. Despite being built primarily on a simple MLP framework, our model demonstrates remarkable performance on both shape classification and shape part segmentation tasks. Our code is available at https://github.com/hitxraz/psvmlp.

Strain and age but not maternal feeding of n-3 fatty acids affect the performance of laying hen offspring in a series of associative learning tasks

Commercial poultry are typically fed diets with fatty acid compositions that differ considerably from wild-type diets in the omega-6 to omega-3 FA ratio (n-6: n-3). Maternal dietary n-3 FA have been shown to affect offspring brain development and cognition in various avian and mammalian species. This study explored the effects of feeding egg-type layer breeders with flaxseed on the performance of their female offspring in a three-stage discrimination task. Shaver White and ISA Brown breeders were fed either a control diet (n-6: n-3 = 14.7:1) or a flaxseed-enriched diet (n-6: n-3 = 5.3:1) throughout the rearing and laying phases. At 30 and 36 weeks of age, eggs were collected, incubated and hatched. Offspring were housed in enriched floor pens and received a control diet. At 12 (pullets) and 33 (hens) weeks of age, three learning tasks were conducted: behavioural shaping (N=437), discrimination test (N=350), and reversal learning (N=213). Food rewards (sweetcorn and raisins) were placed in the “reward” cup. Behavioural shaping consisted of five phases (P): P1 clear cup, P2 coloured cup, P3 coloured cup half-covered with a lid, P4 coloured cup three quarter covered with a lid, and P5 coloured cup covered with a lid. One cup, alternating between blue and green, was presented. Chickens had to eat the food reward from the cup in 4/5 trials to pass each phase. Two cups (green and blue) were presented during discrimination testing and reversal learning with food only in the predetermined “reward” cup. Learning criterion was choosing the correct cup in 4/5 trials for three consecutive days in discrimination testing and for two consecutive days in reversal learning. Data were analysed using survival class analyses. The hazard ratio (HR), 95% confidence intervals (CI) [LL, UL] and p-values to determine the probability of reaching learning criteria are reported. In P1 of behavioural shaping, Brown hens were likelier to reach criteria (HR=2.28, 95% CI [1.48, 3.55], p<0.001). For overall success in behavioural shaping (P1–5), hens were likelier to reach criteria than pullets (HR=2.42, 95% CI [1.50, 3.91], p<0.001). White chickens were likelier to reach criteria in the discrimination test than Brown chickens (HR=1.03, 95% CI [1.01, 1.75], p=0.04). Finally, pullets were likelier to reach criteria in reversal learning than hens (HR=0.44, 95% CI [0.23, 0.86], p=0.016). These results show that age, strain, and their interaction, but not maternal n-3 FA diet, affected the success of chickens in learning tasks.

Leveraging Data Locality in Quantum Convolutional Classifiers.

Quantum computing (QC) has opened the door to advancements in machine learning (ML) tasks that are currently implemented in the classical domain. Convolutional neural networks (CNNs) are classical ML architectures that exploit data locality and possess a simpler structure than a fully connected multi-layer perceptrons (MLPs) without compromising the accuracy of classification. However, the concept of preserving data locality is usually overlooked in the existing quantum counterparts of CNNs, particularly for extracting multifeatures in multidimensional data. In this paper, we present an multidimensional quantum convolutional classifier (MQCC) that performs multidimensional and multifeature quantum convolution with average and Euclidean pooling, thus adapting the CNN structure to a variational quantum algorithm (VQA). The experimental work was conducted using multidimensional data to validate the correctness and demonstrate the scalability of the proposed method utilizing both noisy and noise-free quantum simulations. We evaluated the MQCC model with reference to reported work on state-of-the-art quantum simulators from IBM Quantum and Xanadu using a variety of standard ML datasets. The experimental results show the favorable characteristics of our proposed techniques compared with existing work with respect to a number of quantitative metrics, such as the number of training parameters, cross-entropy loss, classification accuracy, circuit depth, and quantum gate count.

Impairment in acquisition of conditioned fear in people with depressive symptoms.

Depression is one of the primary global public health issues, and there has been a dramatic increase in depression levels among young people over the past decade. The neuroplasticity theory of depression postulates that a malfunction in neural plasticity, which is responsible for learning, memory, and adaptive behavior, is the primary source of the disorder's clinical manifestations. Nevertheless, the impact of depression symptoms on associative learning remains underexplored. We used the differential fear conditioning paradigm to investigate the effects of depressive symptoms on fear acquisition and extinction learning. Skin conductance response (SCR) is an objective evaluation indicator, and ratings of nervousness, likeability, and unconditioned stimuli (US) expectancy are subjective evaluation indicators. In addition, we used associability generated by a computational reinforcement learning model to characterize the skin conductance response. The findings indicate that individuals with depressive symptoms exhibited significant impairment in fear acquisition learning compared to those without depressive symptoms based on the results of the skin conductance response. Moreover, in the discrimination fear learning task, the skin conductance response was positively correlated with associability, as estimated by the hybrid model in the group without depressive symptoms. Additionally, the likeability rating scores improved post-extinction learning in the group without depressive symptoms, and no such increase was observed in the group with depressive symptoms. The study highlights that individuals with pronounced depressive symptoms exhibit impaired fear acquisition and extinction learning, suggesting a possible deficit in associative learning. Employing the hybrid model to analyze the learning process offers a deeper insight into the associative learning processes of humans, thus allowing for improved comprehension and treatment of these mental health problems.

Why do individuals with Williams syndrome or Down syndrome fail the Weather Prediction Task?

Williams syndrome (WS) and Down syndrome (DS) are two neurodevelopmental disorders with distinct genetic origins characterized by mild to moderate intellectual disability. Individuals with WS or DS exhibit impaired hippocampus-dependent place learning and enhanced striatum-dependent spatial response learning. Here, we used the Weather Prediction Task (WPT), which can be solved using hippocampus- or striatum-dependent learning strategies, to determine whether individuals with WS or DS exhibit similar profiles outside the spatial domain. Only 10% of individuals with WS or DS solved the WPT. We further assessed whether a concurrent memory task could promote reliance on procedural learning to solve the WPT in individuals with WS but found that the concurrent task did not improve performance. To understand how the probabilistic cue-outcome associations influences WPT performance, and whether individuals with WS or DS can ignore distractors, we assessed performance using a visual learning task with differing reward contingencies, and a modified WPT with unpredictive cues. Both probabilistic feedback and distractors negatively impacted the performance of individuals with WS or DS. These findings are consistent with deficits in hippocampus-dependent learning and executive functions, and reveal the importance of congruent feedback and the minimization of distractors to optimize learning in these two populations.