Learning Paradigm Research Articles

Individual differences in the acquisition of shared syntactic representations: a re-analysis of studies using an artificial language learning paradigm

Individual differences in the acquisition of shared syntactic representations: a re-analysis of studies using an artificial language learning paradigm

A Metric-Based Detection System for Large Language Model Texts

More efforts are being put into improving Large Language Models’ (LLM) capabilities than into dealing with their implications. Current LLMs are able to generate high quality texts seemingly indistinguishable from those written by human experts. While offering great potentials, such breakthroughs also pose new challenges for safe and ethical uses of LLMs in education, science, and a multitude of other areas. To add up, the majority of current approaches in LLM text detection are either computationally expensive or need access to the LLMs’ internal computations, both of which hinder their public accessibility. With such motivation, this paper presents a novel metric learning paradigm for detection of LLM-generated texts that is able to balance among computational costs, accessibility, and performances. Specifically, the detection is based on learning a similarity function between a given text and an equivalent example generated by LLMs that outputs high values for LLM-LLM text pairs and low values for LLM-human text pairs. In terms of architecture, the detection framework includes a pretrained language model for the text embedding task and a newly designed deep metric model. The metric component can be trained on triplets or pairs of same-context instances to signify the distances between human texts and LLM ones while reducing that among LLM texts. Next, we develop five datasets totalling over 95,000 contexts and triplets of responses in which one from human and two from GPT-3.5 TURBO or GPT-4 TURBO for benchmarking. Experiment studies show that our best architectures maintain F1 scores in between 0.87 to 0.95 across the tested corpora in multiple experiment settings. The metric framework also demands significantly less time in training and inference compared to the RoBERTa, LLaMA 3, Mistral v0.3, and Ghostbuster, while keeping 90% to 150% performances of the best benchmark.

A combinatorial neural code for long-term motor memory.

Motor skill repertoire can be stably retained over long periods, but the neural mechanism that underlies stable memory storage remains poorly understood1-8. Moreover, it is unknown how existing motor memories are maintained as new motor skills are continuously acquired. Here we tracked neural representation of learned actions throughout a significant portion of the lifespan of a mouse and show that learned actions are stably retained in combination with context, which protects existing memories from erasure during new motor learning. We established a continual learning paradigm in which mice learned to perform directional licking in different task contexts while we tracked motor cortex activity for up to six months using two-photon imaging. Within the same task context, activity driving directional licking was stable over time with little representational drift. When learning new task contexts, new preparatory activity emerged to drive the same licking actions. Learning created parallel new motor memories instead of modifying existing representations. Re-learning to make the same actions in the previous task context re-activated the previous preparatory activity, even months later. Continual learning of new task contexts kept creating new preparatory activity patterns. Context-specific memories, as we observed in the motor system, may provide a solution for stable memory storage throughout continual learning.

Alternative Learning Paradigms for Image Quality Transfer

Image Quality Transfer (IQT) aims to enhance the contrast and resolution of low-quality medical images, e.g. obtained from low-power devices, with rich information learned from higher quality images. In contrast to existing IQT methods in the literature which adopt supervised learning frameworks, in this work, we propose two novel formulations of the IQT problem. The first approach uses an unsupervised learning framework, whereas the second is a combination of both supervised and unsupervised learning. The unsupervised learning approach considers a sparse representation (SRep) and dictionary learning model, which we call IQT-SRep, whereas the combination of supervised and unsupervised learning ap- proach is based on deep dictionary learning (DDL), which we call IQT-DDL. The IQT-SRep approach trains two dictionaries using a sparse representation model using pairs of low- and high-quality volumes. Subsequently, the sparse representation of a low-quality block, in terms of the low-quality dictionary, can be directly used to recover the corresponding high-quality block using the high-quality dictionary. On the other hand, the IQT-DDL ap- proach explicitly learns a high-resolution dictionary to upscale the input volume, while the entire network, including high dictionary generator, is simultaneously optimised to take full advantage of deep learning methods. The two models are evaluated using a low-field mag- netic resonance imaging (MRI) application aiming to recover high-quality images akin to those obtained from high-field scanners. Experiments comparing the proposed approaches against state-of-the-art supervised deep learning IQT method (IQT-DL) identify that the two novel formulations of the IQT problem can avoid bias associated with supervised meth- ods when tested using out-of-distribution data that differs from the distribution of the data the model was trained on. This highlights the potential benefit of these novel paradigms for IQT.

Female Wistar Kyoto More Immobile rats with genetic stress hyper-reactivity show enhanced contextual fear memory without deficit in extinction of fear.

The prevalence of post-traumatic stress disorder (PTSD) is higher in females than males, but pre-clinical models are established almost exclusively in males. This study is aimed to investigate the stress-enhanced fear learning model of PTSD in females. The model mirrors PTSD symptomology in males, whereby prior stress leads to extinction resistant exaggerated contextual fear memory. As stress reactivity is highly relevant to the study and risk for PTSD, females of the stress hyper-reactive Wistar Kyoto More Immobile (WMI) and its nearly isogenic control the Wistar Kyoto Less Immobile (WLI) strains were employed. Prior studies have shown WMI females presenting unchanged or enhanced fear memory in the stress-enhanced fear learning paradigm compared WLIs. The present study confirmed the enhanced fear memory following contextual fear conditioning in WMIs compared to WLI females, but this increased fear memory was neither exaggerated by prior stress nor showed extinction deficit. The novel stressor of a glucose challenge test resulted in subtle strain- and prior stress-induced differences in plasma glucose responses. However, fasting plasma corticosterone levels were lower, and rose slower in response to glucose challenge in WMI females, suggesting a PTSD-like dysfunctional stress response. Hippocampal expressions of genes relevant to both learning and memory and the stress response were decreased in stressed WMIs compared to WLI females, further suggesting a marked dysregulation in stress-related functions like in PTSD. Thus, although WMI females do not show extinction-resistant enhanced fear memory, they do present other characteristics that are relevant to PTSD in women.

Demonstrative Learning for Human-Agent Knowledge Transfer

Demonstrative learning in virtual reality (VR) is a pivotal learning strategy for knowledge transfer for embodied agents. While existing studies have extensively explored agents’ knowledge transfer through self-demonstrative learning (SDL) or teacher-demonstrative learning (TDL), there has been limited focus on a system that integrates both paradigms. This paper proposes a comprehensive system that combines the SDL paradigm with the TDL paradigm in VR from a top-down perspective. The system involves using directed probabilistic graphs (DPGs) for knowledge representation, constructing detectors and actuators based on object fluents and atomic actions, representing knowledge acquired from both learning paradigms on the DPGs, and incorporating knowledge integration and visualization. Through system evaluation, we show the advantages of integrating two demonstrative learning paradigms, including increased learning efficiency, mitigating demonstrator's deficiencies, and more logical task execution. The study also reveals that a dynamically decreasing fusion factor with the learning progresses, performs well across different correct percentages of teacher demonstrations. Additionally, we show a more decentralized demonstration in the middle of the agent's learning progress maximizing learning efficiency when demonstrating only a few atomic actions. Finally, we assess the system's generalizability and delineate its boundaries. With the ongoing development and the increasing availability of human data in VR, we anticipate that our system can be applied to future scenarios of efficient human-agent knowledge transfer in human-agent symbiosis.

Integrating spoken instructions into flight trajectory prediction to optimize automation in air traffic control

The booming air transportation industry inevitably burdens air traffic controllers’ workload, causing unexpected human factor-related incidents. Current air traffic control systems fail to consider spoken instructions for traffic prediction, bringing significant challenges in detecting human errors during real-time traffic operations. Here, we present an automation paradigm integrating controlling intent into the information processing loop through the spoken instruction-aware flight trajectory prediction framework. A 3-stage progressive multi-modal learning paradigm is proposed to address the modality gap between the trajectory and spoken instructions, as well as minimize the data requirements. Experiments on a real-world dataset show the proposed framework achieves flight trajectory prediction with high predictability and timeliness, obtaining over 20% relative reduction in mean deviation error. Moreover, the generalizability of the proposed framework is also confirmed by various model architectures. The proposed framework can formulate full-automated information processing in real-world air traffic applications, supporting human error detection and enhancing aviation safety.

Co-clustering: A Survey of the Main Methods, Recent Trends, and Open Problems

Since its early formulations, co-clustering has gained popularity and interest both within and outside the machine learning community as a powerful learning paradigm for clustering high-dimensional data with good explainability properties. The simultaneous partitioning of all the modes of the input data tensors (rows and columns in a data matrix) is both a method for improving clustering on one mode while performing dimensionality reduction on the other mode(s), and a tool for providing an actionable interpretation of the clusters in the main mode as summaries of the features in each other mode(s). Hence, it is useful in many complex decision systems and data science applications. In this article, we survey the the co-clustering literature by reviewing the main co-clustering methods, with a special focus on the work done in the past 25 years. We identify, describe, and compare the main algorithmic categories and provide a practical characterization with respect to similar unsupervised techniques. Additionally, we try to explain why it is still a powerful tool despite the apparent recent decreasing interest shown by the machine learning community. To this purpose, we review the most recent trends in co-clustering research and outline the open problems and promising future research perspectives.

Conflict during learning reconfigures the neural representation of positive valence and approach behavior.

Punishing and rewarding experiences can change the valence of sensory stimuli and guide animal behavior in opposite directions, resulting in avoidance or approach. Often, however, a stimulus is encountered with both positive and negative experiences. How is such conflicting information represented in the brain and resolved into a behavioral decision? We address this question by dissecting a circuit for sexual conditioning in C.elegans. In this learning paradigm, an odor is conditioned with both a punishment (starvation) and a reward (mates), resulting in odor approach. We find that negative and positive experiences are both encoded by the neuropeptide pigment dispersing factor 1 (PDF-1) being released from, and acting on, different neurons. Each experience creates a distinct memory in the circuit for odor processing. This results in the sensorimotor representation of the odor being different in naive and sexually conditioned animals, despite both displaying approach. Our results reveal that the positive valence of a stimulus is not represented in the activity of any single neuron class but flexibly represented within the circuit according to the experiences and predictions associated with the stimulus.

Supramammillary Theta Oscillations in Water Maze Learning.

The supramammillary nucleus (SuM) in the hypothalamus, in conjunction with the hippocampus (HPC), has been implicated through theta oscillations in various brain functions ranging from locomotion to learning and memory. While the indispensable role of the SuM in HPC theta generation in anesthetized animals is well-characterized, the SuM is not always necessary for HPC theta in awake animals. This raises questions on the precise behavioral relevance of SuM theta activity and its interaction with HPC theta activity. We used simultaneously recorded SuM and HPC local field potentials (LFPs) in a one-day water maze (WM) learning paradigm in rats (n = 8), to show that theta activities recorded from the SuM itself were not positively correlated with locomotor (swimming) speed nor acceleration, but the individual relationship between acceleration and SuM theta frequency is correlated with WM learning rates. In contrast, we found that SuM-HPC theta phase coherence is strongly correlated with swimming speed and acceleration, but these do not relate to WM learning. SuM-HPC-directed coherence analysis demonstrated no swimming kinetics nor learning rate associations, but revealed that periods of high SuM-HPC theta phase coherence are driven by the SuM at relatively low (~6.2 Hz) frequencies. Additionally, we demonstrate that the SuM and the HPC also engage in non-random, non-coherent phase coupling modes where either structure preferentially displays a ± 2 Hz difference with the other. Our data indicate SuM theta LFPs do not appear to be related to either speed coding or spatial learning in swimming rats and display non-random out-of-phase theta frequency coupling with the HPC.

Catalyzing IVF outcome prediction: exploring advanced machine learning paradigms for enhanced success rate prognostication

This study addresses the research problem of enhancing In-Vitro Fertilization (IVF) success rate prediction by integrating advanced machine learning paradigms with gynecological expertise. The methodology involves the analysis of comprehensive datasets from 2017 to 2018 and 2010–2016. Machine learning models, including Logistic Regression, Gaussian NB, SVM, MLP, KNN, and ensemble models like Random Forest, AdaBoost, Logit Boost, RUS Boost, and RSM, were employed. Key findings reveal the significance of patient demographics, infertility factors, and treatment protocols in IVF success prediction. Notably, ensemble learning methods demonstrated high accuracy, with Logit Boost achieving an accuracy of 96.35%. The implications of this research span clinical decision support, patient counseling, and data preprocessing techniques, highlighting the potential for personalized IVF treatments and continuous monitoring. The study underscores the importance of collaboration between gynecologists and data scientists to optimize IVF outcomes. Prospective studies and external validation are suggested as future directions, promising to further revolutionize fertility treatments and offer hope to couples facing infertility challenges.

Lifelong learning paradigm and socioeconomic sustainability: towards employment growth of vocational trainers in Pakistan

Lifelong learning paradigm and socioeconomic sustainability: towards employment growth of vocational trainers in Pakistan

Explainable machine learning by SEE-Net: closing the gap between interpretable models and DNNs

Deep Neural Networks (DNNs) have achieved remarkable accuracy for numerous applications, yet their complexity often renders the explanation of predictions a challenging task. This complexity contrasts with easily interpretable statistical models, which, however, often suffer from lower accuracy. Our work suggests that this underperformance may stem more from inadequate training methods than from the inherent limitations of model structures. We hereby introduce the Synced Explanation-Enhanced Neural Network (SEE-Net), a novel architecture integrating a guiding DNN with a shallow neural network, functionally equivalent to a two-layer mixture of linear models. This shallow network is trained under the guidance of the DNN, effectively bridging the gap between the prediction power of deep learning and the need for explainable models. Experiments on image and tabular data demonstrate that SEE-Net can leverage the advantage of DNNs while providing an interpretable prediction framework. Critically, SEE-Net embodies a new paradigm in machine learning: it achieves high-level explainability with minimal compromise on prediction accuracy by training an almost “white-box” model under the co-supervision of a “black-box” model, which can be tailored for diverse applications.

Semantics and instance interactive learning for labeling and segmentation of vertebrae in CT images

Automatically labeling and segmenting vertebrae in 3D CT images compose a complex multi-task problem. Current methods progressively conduct vertebra labeling and semantic segmentation, which typically include two separate models and may ignore feature interaction among different tasks. Although instance segmentation approaches with multi-channel prediction have been proposed to alleviate such issues, their utilization of semantic information remains insufficient. Additionally, another challenge for an accurate model is how to effectively distinguish similar adjacent vertebrae and model their sequential attribute. In this paper, we propose a Semantics and Instance Interactive Learning (SIIL) paradigm for synchronous labeling and segmentation of vertebrae in CT images. SIIL models semantic feature learning and instance feature learning, in which the former extracts spinal semantics and the latter distinguishes vertebral instances. Interactive learning involves semantic features to improve the separability of vertebral instances and instance features to help learn position and contour information, during which a Morphological Instance Localization Learning (MILL) module is introduced to align semantic and instance features and facilitate their interaction. Furthermore, an Ordinal Contrastive Prototype Learning (OCPL) module is devised to differentiate adjacent vertebrae with high similarity (via cross-image contrastive learning), and simultaneously model their sequential attribute (via a temporal unit). Extensive experiments on several datasets demonstrate that our method significantly outperforms other approaches in labeling and segmenting vertebrae. Our code is available at https://github.com/YuZhang-SMU/Vertebrae-Labeling-Segmentation

Robust and energy-efficient RPL optimization algorithm with scalable deep reinforcement learning for IIoT

The increasing complexity and quantity of the Industrial Internet of Things (IIoT) pose new challenges to the traditional routing protocol for low-power and lossy networks (RPL) in terms of dynamic management, data transmission reliability, and energy efficiency optimization. This paper proposes a scalable deep reinforcement learning (DRL) algorithm with a multi-attention actor double critic model for routing optimization (MADC) to meet the requirements of IIoT for efficient and intelligent routing decisions while improving data transmission reliability and energy efficiency. Specifically, MADC employs the centralized training and decentralized execution (CTDE) learning paradigm to decouple the model’s training and inference tasks, which reduces the difficulty and computational cost of model learning and improves the training efficiency. In addition, a lightweight actor network based on multi-scale convolutional attention mechanism is designed in MADC, which can provide intelligent and real-time decision-making capabilities for resource-constrained nodes with low computational and storage complexities. Moreover, a scalable critic network utilizing multiple attention mechanisms is proposed. It is not only suitable for dynamic and changing network environments but also can more comprehensively and accurately evaluate local observation states, providing more accurate and efficient guidance for model optimization. Furthermore, MADC incorporates a double critic network architecture to mitigate potential overestimation issues during training, thereby ensuring the model’s robustness and reliability. Simulation results demonstrate that MADC outperforms existing RPL optimization algorithms in terms of energy efficiency, data transmission reliability, and adaptability.

SecDefender: Detecting low-quality models in multidomain federated learning systems

Federated learning (FL) is an innovative distributed learning paradigm that permits multiple parties to train models collaboratively while protecting individual privacy. However, it encounters security challenges, making it vulnerable to several adversarial attacks and leading to compromising model performance. Existing research on FL poisoning attacks and defense techniques tends to be application-specific, primarily emphasizing attack capabilities. However, it fails to consider inherent vulnerabilities in FL and the impact of attack intensity. To our knowledge, no existing work has delved into these issues within a multi-domain FL environment. This paper addresses these concerns by investigating the consequences of targeted label-flipping attacks within FL systems and comprehensively examining the effects of the attacks in single-label, double-label, and triple-label scenarios with different levels of poisoning intensities. Additionally, we investigate the influence of a temporal label-flipping attack, where we study the impact of adversaries available only for specific federated training rounds. Moreover, we propose a novel server-based defense mechanism called SecDefender to detect low-quality models in both IID and non-IID settings of multi-domain environments. Our approach is rigorously evaluated against state-of-the-art alternatives using six benchmark datasets: CIC-Darknet2020, Fashion-MNIST, FEDMNIST, GTSR, HAR, and MNIST. Extensive experiments demonstrate that our proposed SecDefender significantly enhances its performance by over 65% in terms of source class recall, maintaining a low attack success rate. Consequently, there is a 1 to 2% enhancement in global model accuracy compared to existing approaches.

Multi-attribute dynamic attenuation learning improved spiking actor network

Deep reinforcement learning (DRL) has shown promising results in solving robotic control and decision tasks, which can learn the high-dimensional state and action information well. Despite their successes, conventional neural-based DRL models are criticized for low energy efficiency, making them laborious to be widely applied in low-power electronics. With more biologically plausible plasticity principles, spiking neural networks (SNNs) are now considered an energy-efficient and robust alternative. The most existing dynamics and learning paradigms for spiking neurons with a common Leaky Integrate-and-Fire (LIF) neuron model often result in relatively low efficiency and poor robustness. To address these limitations, we propose a multi-attribute dynamic attenuation learning improved spiking actor network (MADA-SAN) for reinforcement learning to achieve effective decision-making. The resistance, membrane voltage and membrane current of spiking neurons are updated from a fixed value into dynamic attenuation. By enhancing the temporal relation dependencies in neurons, this model can learn the spatio-temporal relevance of complex continuous information well. Extensive experimental results show MADA-SAN performs better than its counterpart deep actor network on six continuous control tasks from OpenAI gym. Besides, we further validated the proposed MADA-LIF can achieve comparable performance with other state-of-the-art algorithms on MNIST and DVS-gesture recognition tasks.

Transforming learning outcomes: Impact of project-based learning on digestive system mastery

One of the learning models that is currently strongly advised to be used in the learning process is Project Based Learning (PJBL). The purpose of this study is to ascertain how PJBL affects students' learning outcomes in the digestive system. Students (n=61) from Muara Enim, Indonesia's class XI Science public senior high school served as the research subjects. A quasi-experimental design with a non-equivalent control group is the study methodology employed. Project assignments, surveys, and observation sheets served as the tools. The independent sample t-test in the statistical program for social science 28 (SPSS version 28) was used to assess learning outcomes data. With a gain of 33.6 and n-gain of 0.63, the study's findings show that using the PjBL learning paradigm enhances students' learning outcomes. PjBl can increase motivation, and as it uses real-world challenges, strong curiosity will impact learning outcomes.

Influenced of Discovery Learning Model Assisted by iSpring Presenter on Students HOT Literacy Redox Reactions

This research aims to determine the influence of the discovery learning model assisted by iSpring presenter media which is greater than the conventional model on students' chemistry literacy HOT abilities and aspects of developed HOTS literacy abilities. Three classes of class X pupils from SMAS Imelda Medan made up the study's population. Thirty students each from classes X MIA 2 and X MIA 3 made up the research sample. Nineteen multiple-choice questions made up the test instrument used in the study Hypothesis testing used the right-hand t test with the research results obtained by the value tcount > ttable (2.243 > 2.002) meaning that Ha was accepted and H0 was rejected, which means that the influence of using the discovery learning model assisted by iSpring presenter media on students' chemical literacy HOT abilities had a greater impact than using the conventional model. on redox reaction material with an N-Gain value of 0.75 (75.03%). Besides that, the HOT literacy skills acquired through the iSpring presenter media-assisted discovery learning paradigm were demonstrated in C5 reasoning with an 87.94% percentage in the redox reaction material.

Integrating genomic and molecular data to predict antimicrobial minimum inhibitory concentration in Klebsiella pneumoniae

Minimum inhibitory concentration (MIC) denotes the in vitro benchmark indicating the quantity of antibiotic required to inhibit proliferation of specific bacterial strains. Determining MIC values corresponding to the infecting bacterial strain is paramount for tailoring appropriate antibiotic therapy. In the interim between specimen collection and laboratory-derived MIC outcomes, clinicians frequently resort to empirical therapy informed by retrospective analyses. Here introduces two deep learning approaches, a Convolutional Neural Network (CNN)-based model and an Enformer-based model, integrating genomic data of Klebsiella Pneumoniae and molecular structural data of 20 antibiotics to anticipate the MIC value of the bacterium for each antibiotic under consideration. These models demonstrate enhanced raw accuracy over the existing state-of-the-art model, which rely exclusively on genomic data. The CNN-based model achieves a notable 20% increase in raw accuracy while further mirroring the 1-tier accuracy of the state-of-the-art model. Although the Enformer-based model does not quite reach the performance levels of the CNN-based model, it offers an advantage by eliminating the need for arbitrary data processing steps. This streamlining of the data processing pipeline facilitates fast updates and improves the model interpretability. It is expected that these deep learning paradigms can significantly inform and bolster clinician decision-making during the empirical treatment phase.