Learning Task Research Articles

Improving job matching with deep learning-based hyper-personalization

This study introduces a novel approach to streamline the recruitment process, benefiting both employers and job seekers. It leverages real-time personality-based classification to match candidates with the most suitable roles in a scalable and precise manner. This is achieved through machine learning-driven hyper-personalization, employing deep learning models to create a predictive language model. The study encompasses two key tasks: binary classification, distinguishing sentences containing soft skills (1) from those that do not (0), and multi-class classification, categorizing positive sentences into five classes based on Big Five personality traits. The research involved a series of experiments. Initially, multiple machine learning algorithms were employed to establish baseline models. Subsequently, the study investigated the impact of deep learning versus these baseline models. The results demonstrated an accuracy of 0.79% and 0.68% for binary classification tasks, and 0.79% and 0.60% for multi-class classification tasks, using Support Vector Machines in the machine learning task, and Bidirectional Long Short-Term Memory in the deep learning task, respectively. This approach showcases promise in revolutionizing the job matching process, offering a more efficient and accurate means of connecting individuals with their ideal employment opportunities based on their unique soft skills and personality traits.

SRL-VIC: A Variable Stiffness-Based Safe Reinforcement Learning for Contact-Rich Robotic Tasks

SRL-VIC: A Variable Stiffness-Based Safe Reinforcement Learning for Contact-Rich Robotic Tasks

Comparing hybrid models for recognising objects in thermal images at nighttime

This research aims to revolutionize urban object recognition by developing cloud-based Python programs using intelligent algorithms. Unlike current models that focus on colour enhancement in nighttime thermal images, this work addresses the critical challenge of accurate object detection in urban landscapes. The proposed method incorporates a binary generative adversarial network (GAN) generator that can switch bidirectionally between daytime colour (DC) and nighttime infrared (NTIR) images. memory-based visual image memory (MVAM), system extracts important descriptive information from urban landscape images, reducing problems related to small sample sizes. This discussion presents a comprehensive improvement and evaluation of a deep learning image classification pipeline using Google Colab, demonstrating advanced image processing. Using TensorFlow, Keres and scikit image libraries combined with advanced algorithms such as DenseNet121 and MobileNetV2 presents a clear approach. We created a Bidirectional GAN + MVAM for object recognition in this work. Our method performed well, with an accuracy of 81.43%, precision of 51.16, recall of 50.11, and F-score of 46.37. The systematic presentation of the code presents a careful strategy to ensure optimal performance, stability, and efficiency of deep learning and image processing tasks.

One-trial appetitive learning tasks for drug targeting.

One-trial appetitive learning developed from one-trial passive avoidance learning as a standard test of retrograde amnesia. It consists of one learning trial followed by a retention test, in which physiological manipulations are presented. As in passive avoidance learning, food- or water-deprived rats or mice finding food or water inside an enclosure are vulnerable to the retrograde amnesia produced by electroconvulsive shock treatment or the injection of various drugs. In one-trial taste or odor learning conducted in rats, birds, snails, bees, and fruit flies, there is an association between a food item or odorant and contextual stimuli or the unconditioned stimulus of Pavlovian conditioning. The odor-related task in bees was sensitive to protein synthesis inhibition as well as cholinergic receptor blockade, both analogous to results found on the passive avoidance response in rodents, while the task in fruit flies was sensitive to genetic modifications and aging, as seen in the passive avoidance response of genetically modified and aged rodents. These results provide converging evidence of interspecies similarities underlying the neurochemical basis of learning.

Selective Random Walk for Transfer Learning in Heterogeneous Label Spaces.

Transfer learning has been widely used in different scenarios, especially in those lacking enough labeled data. However, most of the existing transfer learning methods are based on the assumption that the source and target domains should share the label space entirely or partially, which greatly limits their application scopes. In this article, a Selective Random Walk (SRW) method for transfer learning in heterogeneous label spaces is proposed to make full use of unlabeled auxiliary data, which acts as a bridge for knowledge transfer from the source domain to the target domain. The proposed SRW method can explicitly identify transfer sequences between source and target instances via auxiliary instances based on random walk techniques. Since not all of the transfer sequences generated by random walk are credible for the target task, the SRW method can learn to weight transfer sequences adaptively. Based on the weights of the transfer sequences, the SRW method leverages knowledge by forcing adjacent data points in the transfer sequence to be similar and making the target data point in the sequence represented by other data points in the same sequence. Experiments show that the SRW method outperforms state-of-the-art models in plenty of transfer learning tasks with heterogeneous label spaces constructed within and across several benchmark datasets.

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.

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

BackgroundDepression 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.MethodsWe 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.ResultsThe 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.ConclusionThe 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.

Developing a novel causal inference algorithm for personalized biomedical causal graph learning using meta machine learning

BackgroundModeling causality through graphs, referred to as causal graph learning, offers an appropriate description of the dynamics of causality. The majority of current machine learning models in clinical decision support systems only predict associations between variables, whereas causal graph learning models causality dynamics through graphs. However, building personalized causal graphs for each individual is challenging due to the limited amount of data available for each patient.MethodIn this study, we present a new algorithmic framework using meta-learning for learning personalized causal graphs in biomedicine. Our framework extracts common patterns from multiple patient graphs and applies this information to develop individualized graphs. In multi-task causal graph learning, the proposed optimized initial guess of shared commonality enables the rapid adoption of knowledge to new tasks for efficient causal graph learning.ResultsExperiments on one real-world biomedical causal graph learning benchmark data and four synthetic benchmarks show that our algorithm outperformed the baseline methods. Our algorithm can better understand the underlying patterns in the data, leading to more accurate predictions of the causal graph. Specifically, we reduce the structural hamming distance by 50-75%, indicating an improvement in graph prediction accuracy. Additionally, the false discovery rate is decreased by 20-30%, demonstrating that our algorithm made fewer incorrect predictions compared to the baseline algorithms.ConclusionTo the best of our knowledge, this is the first study to demonstrate the effectiveness of meta-learning in personalized causal graph learning and cause inference modeling for biomedicine. In addition, the proposed algorithm can also be generalized to transnational research areas where integrated analysis is necessary for various distributions of datasets, including different clinical institutions.

A qualitative content analysis exploring gender representation in language textbooks published by Jammu and Kashmir board of school education

This paper examines gender representation in Jammu and Kashmir Board of School Education (JKBOSE) language textbooks. These books were revised and developed as per the guidelines of National Curriculum Framework (NCF), 2005, which emphasizes on the elimination of gender inequality in education through the design and selection of learning tasks and pedagogic practices. The factors examined include the ratio of male-female appearances, titles of address for both sexes and the roles/activities assigned to males and females. To examine these factors, a method of qualitative content analysis was adopted. The study findings revealed that the revised textbooks lack relevance with the NCF (2005) guidelines and contribute towards the perpetuation of gender inequality. The bias in favor of males is still present in the core curriculum. Male's appearance dominates in written text and titles. Females are shown in their stereotypical gender roles and activities. This study shows concern towards the gender biased approach of curriculum designers and textbook writers; and recommends of producing gender fair educational material based on the guidelines of NCF (2005).

Meta learning based residual network for industrial production quality prediction with limited data

Due to the challenge of collecting a substantial amount of production-quality data in real-world industrial settings, the implementation of production quality prediction models based on deep learning is not effective. To achieve the goal of predicting production quality with limited data and address the issue of model degradation in the training process of deep learning networks, we propose Meta-Learning based on Residual Network (MLRN) models for production quality prediction with limited data. Firstly, the MLRN model is trained on a variety of learning tasks to acquire knowledge for predicting production quality. Furthermore, to obtain more features with limited data and avoid the issues of gradient disappearing or exploding in deep network training, the enhanced residual network with the effective channel attention (ECA) mechanism is chosen as the basic network structure of MLRN. Additionally, a multi-batch and multi-task data input approach is implemented to prevent overfitting. Finally, the availability of the MLRN model is demonstrated by comparing it with other models using both numerical and graphical datasets.

The Use of Cake Application in Learning English Speaking Skills

Technology is quite important to use in everyday lives in this modern day. Young learners nowadays use technology for study and it can assist teachers and students in carrying out learning tasks. There are various applications available right now that can help kids learn more effectively; one such app for learning to speak is the cake app. This study aims to analyze the use of Cake application as a tool to learn English speaking skills. A literature study was conducted in this research. A literature study is a data collecting strategy that comprises doing study studies of books, literature, records, and reports that have to do with issues solved. One of the most important abilities in learning English is speaking and a skill practiced in speaking is how to pronounce words properly and correctly. The Cake program is a tool for learning English. Playlist Corporation's Cake - Learn English for Free in the category of Education is developed by Playlist Corporation. There are several features in this application such as watching short movie and practicing speaking by using dialogue. The research's goal is to look into how Cake Application can be used to learn how to speak.

Training toward significance with the decorrelated event classifier transformer neural network

Experimental particle physics uses machine learning for many tasks, where one application is to classify signal and background events. This classification can be used to bin an analysis region to enhance the expected significance for a mass resonance search. In natural language processing, one of the leading neural network architectures is the transformer. In this work, an event classifier transformer is proposed to bin an analysis region, in which the network is trained with special techniques. The techniques developed here can enhance the significance and reduce the correlation between the network’s output and the reconstructed mass. It is found that this trained network can perform better than boosted decision trees and feed-forward networks. Published by the American Physical Society 2024

Interpretable molecular encodings and representations for machine learning tasks

Molecular encodings and their usage in machine learning models have demonstrated significant breakthroughs in biomedical applications, particularly in the classification of peptides and proteins. To this end, we propose a new encoding method: Interpretable Carbon-based Array of Neighborhoods (iCAN). Designed to address machine learning models' need for more structured and less flexible input, it captures the neighborhoods of carbon atoms in a counting array and improves the utility of the resulting encodings for machine learning models. The iCAN method provides interpretable molecular encodings and representations, enabling the comparison of molecular neighborhoods, identification of repeating patterns, and visualization of relevance heat maps for a given data set. When reproducing a large biomedical peptide classification study, it outperforms its predecessor encoding. When extended to proteins, it outperforms a lead structure-based encoding on 71% of the data sets. Our method offers interpretable encodings that can be applied to all organic molecules, including exotic amino acids, cyclic peptides, and larger proteins, making it highly versatile across various domains and data sets. This work establishes a promising new direction for machine learning in peptide and protein classification in biomedicine and healthcare, potentially accelerating advances in drug discovery and disease diagnosis.

Computational analysis of value learning and value-driven detection of neutral faces by young and older adults

The rapid detection of neutral faces with emotional value plays an important role in social relationships for both young and older adults. Recent psychological studies have indicated that young adults show efficient value learning for neutral faces and the detection of “value-associated faces,” while older adults show slightly different patterns of value learning and value-based detection of neutral faces. However, the mechanisms underlying these processes remain unknown. To investigate this, we applied hierarchical reinforcement learning and diffusion models to a value learning task and value-driven detection task that involved neutral faces; the tasks were completed by young and older adults. The results for the learning task suggested that the sensitivity of learning feedback might decrease with age. In the detection task, the younger adults accumulated information more efficiently than the older adults, and the perceptual time leading to motion onset was shorter in the younger adults. In younger adults only, the reward sensitivity during associative learning might enhance the accumulation of information during a visual search for neutral faces in a rewarded task. These results provide insight into the processing linked to efficient detection of faces associated with emotional values, and the age-related changes therein.

Going back to "basics": Harlow's learning set task with wolves and dogs.

To survive and reproduce, animals need to behave adaptively by adjusting their behavior to their environment, with learning facilitating some of these processes. Dogs have become a go-to model species in comparative cognition studies, making our understanding of their learning skills paramount at multiple levels, not only with regards to basic research on their cognitive skills and the effects of domestication, but also with applied purposes such as training. In order to tackle these issues, we tested similarly raised wolves and dogs in a serial learning task inspired by Harlow's "learning set." In Phase 1, different pairs of objects were presented to the animals, one of which was baited while the other was not. Both species' performance gradually improved with each new set of objects, showing that they "learnt to learn," but no differences were found between the species in their learning speed. In Phase 2, once subjects had learned the association between one of the objects and the food reward, the contingencies were reversed and the previously unrewarded object of the same pair was now rewarded. Dogs' performance in this task seemed to be better than wolves', albeit only when considering just the first session of each reversal, suggesting that the dogs might be more flexible than wolves. Further research (possibly with the aid of refined methods such as computer-based tasks) would help ascertain whether these differences between wolves and dogs are persistent across different learning tasks.

Learning the weights using attribute order information for multi-criteria decision making tasks

AbstractIn multi-criteria decision making, the importance of decision criteria (decision attributes) plays a crucial role. Ranking is a useful technique for expressing the importance of decision criteria in a decision-makers’ preference system. Since weights are commonly utilized for characterizing the importance of criteria, weight determination and assessment are important tasks in multi-criteria decision making and in voting systems as well. In this study, we concentrate on the connection between the preference order of decision criteria and the decision weights. Here, we present an easy-to-use procedure that can be used to produce a sequence of weights corresponding to a decision-makers’ preference order of decision criteria. The proposed method does not require pairwise comparisons, which is an advantageous property especially in cases where the number of criteria is large. This method is based on the application of a class of regular increasing monotone quantifiers, which we refer to as the class of weighting generator functions. We will show that the derivatives of these functions can be used for approximating the criteria weights. Also, we will demonstrate that using weighting generator functions, weights can be inverted in a consistent way. We will deduce the generators for arithmetic and geometric weight sequences, and we will present a one-parameter generator function known as the tau function in continuous-valued logic. We will show that using these weighting generator functions, the weight learning task can be turned into a simple, one-parameter optimization problem.

Enhancing Fault Diagnosis in Industrial Processes through Adversarial Task Augmented Sequential Meta-Learning

This study introduces the Adversarial Task Augmented Sequential Meta-Learning (ATASML) framework, designed to enhance fault diagnosis in industrial processes. ATASML integrates adversarial learning with sequential task learning to improve the model’s adaptability and robustness, facilitating precise fault identification under varied conditions. Key to ATASML’s approach is its novel use of adversarial examples and data-augmentation techniques, including noise injection and temporal warping, which extend the model’s exposure to diverse operational scenarios and fault manifestations. This enriched training environment significantly boosts the model’s ability to generalize from limited data, a critical advantage in industrial applications where anomaly patterns frequently vary. The framework’s performance was rigorously evaluated on two benchmark datasets: the Tennessee Eastman Process (TEP) and the Skoltech Anomaly Benchmark (SKAB), which are representative of complex industrial systems. The results indicate that ATASML outperforms conventional meta-learning models, particularly in scenarios characterized by few-shot learning requirements. Notably, ATASML demonstrated superior accuracy and F1 scores, validating its effectiveness in enhancing fault-diagnosis capabilities. Furthermore, ATASML’s strategic incorporation of task sequencing and adversarial tasks optimizes the training process, which not only refines learning outcomes but also improves computational efficiency. This study confirms the utility of the ATASML framework in significantly enhancing the accuracy and reliability of fault-diagnosis systems under diverse and challenging conditions prevalent in industrial processes.

Enhanced Learning and Memory in Patients with CRB1 Retinopathy

Mutations in the CRB1 gene are associated with a diverse spectrum of retinopathies with phenotypic variability causing severe visual impairment. The CRB1 gene has a role in retinal development and is expressed in the cerebral cortex and hippocampus, but its role in cognition has not been described before. This study compares cognitive function in CRB1 retinopathy individuals with subjects with other retinopathies and the normal population. Methods: Neuropsychological tests of cognitive function were used to test individuals with CRB1 and non-CRB1 retinopathies and compare results with a standardised normative dataset. Results: CRB1 retinopathy subjects significantly outperformed those with non-CRB1 retinopathy in list learning tasks of immediate (p = 0.001) and delayed memory (p = 0.007), tests of semantic verbal fluency (p = 0.017), verbal IQ digit span subtest (p = 0.037), and estimation test of higher execution function (p = 0.020) but not in the remaining tests of cognitive function (p > 0.05). CRB1 retinopathy subjects scored significantly higher than the normal population in all areas of memory testing (p < 0.05) and overall verbal IQ tests (p = 0.0012). Non-CRB1 retinopathy subjects scored significantly higher than the normal population in story recall, verbal fluency, and overall verbal IQ tests (p = 0.0016). Conclusions: Subjects with CRB1 retinopathy may have enhanced cognitive function in areas of memory and learning. Further work is required to understand the role of CRB1 in cognition.

Unifying O(3) equivariant neural networks design with tensor-network formalism

Many learning tasks, including learning potential energy surfaces from ab initio calculations, involve global spatial symmetries and permutational symmetry between atoms or general particles. Equivariant graph neural networks are a standard approach to such problems, with one of the most successful methods employing tensor products between various tensors that transform under the spatial group. However, as the number of different tensors and the complexity of relationships between them increase, maintaining parsimony and equivariance becomes increasingly challenging. In this paper, we propose using fusion diagrams, a technique widely employed in simulating SU(2)-symmetric quantum many-body problems, to design new spatial equivariant components for neural networks. This results in a diagrammatic approach to constructing novel neural network architectures. When applied to particles within a given local neighborhood, the resulting components, which we term ‘fusion blocks,’ serve as universal approximators of any continuous equivariant function defined on the neighborhood. We incorporate a fusion block into pre-existing equivariant architectures (Cormorant and MACE), leading to improved performance with fewer parameters on a range of challenging chemical problems. Furthermore, we apply group-equivariant neural networks to study non-adiabatic molecular dynamics of stilbene cis-trans isomerization. Our approach, which combines tensor networks with equivariant neural networks, suggests a potentially fruitful direction for designing more expressive equivariant neural networks.