Bio-inspired Active Learning method in spiking neural network

This study compares the impact of two active learning methods; Problem-Based Learning (PBL), and Project-Oriented Learning (POL) versus the Traditional Lecture (TL) method on learners' ability to differentiate between monocotyledons and dicotyledons based on their morphological and anatomical characteristics. The research used a quasi-experimental design involving 150 students, divided into three groups: two experimental groups subjected to active learning methods and a control group exposed to traditional lectures. The study used mixed research methods to assess the effectiveness of these teaching strategies. Pre and post-test scores were employed to evaluate learners' improvements and observational techniques were employed to analyse classroom engagement and the development of scientific skills. The results indicate that both active learning methods significantly enhanced learner engagement, understanding, and the application of scientific concepts. The PBL and POL groups demonstrated superior critical thinking, collaboration, and problem-solving skills, with the POL group showing the highest improvement in project management and creative thinking. By contrast, the TL group exhibited moderate improvements, primarily in memorization rather than conceptual understanding. These findings support the growing body of literature that advocates for active learning as an effective alternative to traditional teaching methods in science education. Keywords: Active Learning, Problem-Based Learning, Project-Oriented Learning, Traditional Lecture, Monocots, Dicots. DOI: 10.7176/JEP/16-11-20 Publication date: October 30th 2025

The article is devoted to modern approaches to the development of civic competence of young people. The authors of the article pay special attention to active methods of social learning. In the process of developing programs and trainings on the development of civic competence, it is advisable to use such methods of active learning, which in working with students should be: relevant to the target audience, contain innovative components, and meet the requirements of higher education. The article presents the author's socio-psychological program for the development of civic competence of young people using social media and media content. The article presents the author's social and psychological program for the development of civic competence of young people using social media and media content. The main directions of development of civic competence in the program are: 1) reflection on citizenship, experience of interaction with authorities at the national and local levels, 2) development of civic skills, acquisition / renewal of experience in solidarity and civic participation, 3) actualization of readiness to apply the acquired experience (knowledge, skills and abilities) in real situations of interaction. The program uses both traditional methods of active social learning and social media and media content. The method of web-quests is used to update the target and instrumental motives for the use of social media; to master the instrumental skills of constructive interaction with central and local authorities by digital means, as well as an effective means of mastering proactive roles to ensure constructive interaction with government institutions, civic society, groups and communities on social networks. The comics method is used to update individual components of civic competence and diagnose changes in strategies and ways of interacting with public authorities. The proposed program for the development of civic competence has been successfully tested.

Comparative educational outcomes of an active versus passive learning continuing professional development activity on self-management support for respiratory educators: A non-randomized controlled mixed-methods study

Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples given by the active user, the more accurate the predicted ratings will be. Active learning provides an effective way to acquire the most informative rated examples from active users. Previous work on active learning for collaborative filtering only considers the expected loss function based on the estimated model, which can be misleading when the estimated model is inaccurate. This paper takes one step further by taking into account of the posterior distribution of the estimated model, which results in more robust active learning algorithm. Empirical studies with datasets of movie ratings show that when the number of ratings from the active user is restricted to be small, active learning methods only based on the estimated model don't perform well while the active learning method using the model distribution achieves substantially better performance.

The objectives of the research are to prepare skill exercises in the active learning method according to the fink model and to identify the effect of skill exercises in the active learning method on some cognitive skills, motor satisfaction and offensive skills with basketball, and the researcher assumed there are statistically significant differences between the results of the pre and post tests in favor of the post tests for the control groups And there are differences of statistical significance between the results of the post tests of the experimental and control groups in favor of the experimental group, and it includes the human, temporal and spatial domains. It includes addressing the movement programs and how to form them and the method of active learning according to the fink model, and the basic skills of basketball The control group (10) students, as well as includes the tools and means that were used in research, skill tests, and the scientific basis for the tests and pre-tests, and ensures the application of the active learning method according to the fink model, post-tests, and statistical means. The presentation, analysis and discussion of the results included the pre and post tests of the two experimental and control groups for the skills of chest handling and the change of direction. It included the conclusions and recommendations reached by the researcher, which are: The preference of the exercises prepared by the researcher over the exercises followed by the teacher, and the researcher recommended the necessity of using the active learning method according to The fink model in the learning process.

Recognizing and nurturing all the varieties of human intelligences is essential for exploring the talents of students and enabling their identification of multiple intelligences. Studies have suggested that eliciting the maximum potential of intelligences leads to students' success in their academic and future careers. The literature has shown that incorporating active learning into the teaching and learning of moral education to develop multiple intelligences is limited. Accordingly, this study aims to discover the various intelligences that exist among moral education students through the active learning method. Active learning implies that all learners are provided with time and assistance to realize their potential. In this regard, multiple intelligence theory is used as the theoretical framework for defining, understanding, developing, and estimating the various intelligences that students have. The research design for this study is the qualitative method. A total of fourteen students from two schools were chosen as research participants. Data were collected through observation, focus group interviews, and journal entries. These findings reveal that using the active learning method in moral education can develop students’verbal linguistic intelligence, logical–mathematical intelligence, musical intelligence, spatial intelligence, bodily kinesthetic intelligence, intrapersonal intelligence, interpersonal intelligence, and naturalistic intelligence. Integration and internalization of the eight intelligences into active learning holistically will shape the personality and character of students in social life.

Spiking Neural Networks (SNNs) have emerged as an attractive alternative to traditional deep learning frameworks, since they provide higher computational efficiency in event driven neuromorphic hardware. However, the state-of-the-art (SOTA) SNNs suffer from high inference latency, resulting from inefficient input encoding and training techniques. The most widely used input coding schemes, such as Poisson based rate-coding, do not leverage the temporal learning capabilities of SNNs. This paper presents a training framework for low-latency energy-efficient SNNs that uses a hybrid encoding scheme at the input layer in which the analog pixel values of an image are directly applied during the first timestep and a novel variant of spike temporal coding is used during subsequent timesteps. In particular, neurons in every hidden layer are restricted to fire at most once per image which increases activation sparsity. To train these hybrid-encoded SNNs, we propose a variant of the gradient descent based spike timing dependent backpropagation (STDB) mechanism using a novel cross entropy loss function based on both the output neurons' spike time and membrane potential. The resulting SNNs have reduced latency and high activation sparsity, yielding significant improvements in computational efficiency. In particular, we evaluate our proposed training scheme on image classification tasks from CIFAR-10 and CIFAR-100 datasets on several VGG architectures. We achieve top-l accuracy of 66.46% with 5 timesteps on the CIFAR-100 dataset with ~125x less compute energy than an equivalent standard ANN. Additionally, our proposed SNN performs 5–300 x faster inference compared to other state-of-the-art rate or temporally coded SNN models.

Metallocene and Single Site Polymers (#1624)

Comparison of sampling strategies for object-based classification of urban vegetation from Very High Resolution satellite images

We consider the problem of SVM batch active learning, which involves distinguishing samples chosen and maximum approximate the real normal vector w in feature space. Although several studies are devoted to batch mode active learning, they suffer either from the uncertain parameter set or from the solutions of local optimization. We introduce a new algorithm for performing batch active learning by cluster diversity and most possibly error approximate method. Experimental results showing that employing our active learning method can significantly reduce the computational cost as well as excellent learning performance in comparison with other active learning methods.

Penelitian ini bertujuan untuk mendeskripsikan penerapan metode PAKEM dalam meningkatkan keterampilan siswa membaca puisi sekolah mitra SMP Negeri 13 Langsa dengan menggunakan metode penelitian tindakan kelas. Peningkatkan kemampuan siswa membaca puisi dengan metode konvensionalmasih rendah pada Kelas VIII SMP Negeri 13 Langsa. Permasalahan dalam penelitian ini adalah apakah pembelajaran dengan metode PAKEM dapat meningkatkan kemampuan siswa dalam membaca puisi pada Kelas VIII SMP Negeri 13 Langsa. Subjek penelitian ini adalah siswa Kelas VIII SMP Negeri 13 Langsa yang berjumlah 29 Siswa yang dijadikan sebagai sampel penelitian. Objek penelitian adalah penerapan metode PAKEM. Alat dalam pengumpulan data adalah pengamatan, observasi, dan penugasan dengan jalur siklus, yaitu siklus I dan siklus II, pada siklus I nilai rata-rata 53,6 dengan ketuntasan 24,13%. Pada siklus II meningkatkan menjadi 78,9 dengan ketuntasan 86,2%, berarti hasil meningkat pada siklus II (tuntas). Dengan demikian hasil penerapan metode pakem dalam meningkatkan keterampilan siswa membaca puisi sekolah mitra SMP Negeri 13 Langsa terjadi peningkatan 60,07%

Purpose: This research indicates the need to identify the right teaching and learning methods, ways to design teaching and learning methods for lecturers, and students in Vietnam's higher education system. From there, point out the limitations of current teaching methods and the advantages when teachers and learners design their new teaching and learning methods. Methodology: This research uses qualitative and quantitative research methods through interviews about teaching methods of lecturers and student learning methods; evaluation of lecturers and students about the advantages and disadvantages of the current teaching and learning method. Respondents included 1.000 students and 130 lecturers at several universities in the Ho Chi Minh City of Vietnam. Main Finding: Based on these data and analysis, this study shown a new paradigm in developing active teaching and learning methods for lecturers and students, optimal methods for achieving the expectations that teaching strategies and active learning by the instructors and students. Implications/Applications: This study contributes to the development of positive teaching and learning strategies, creating interest, and promoting students' self-study ability. The results will help lecturers, and students build proper teaching and learning strategies, creating funny, development capacity, and creativity of students. Novelty/Originality: The research, analyze and design the essential contents of the strategy development process for both teachers (lecturers) and learners (students). The main contributions of the research are the initial conditions necessary for teachers and students to develop effective teaching and learning strategies for themselves.

The main purpose of this study was to assess the current practices and challenges of active learning in Amhara Region Police College in teaching police science. To congregate the objective of the study, mixed research design was employed. Simple random sampling for cadets and census method for instructors’ was used to select cadets and instructors of Amhara Region Police College. Quantitative data were collected from cadets and instructors using structured and pretested questionnaire. The academic director and research department head were interviewed using interview guide. Data analysis was done in three phases. First, analysis of the quantitative data was done in SPSS Version 24 and percentages, means and a frequency, second, qualitative data was analyzed considering the research question, by using descriptive which is a deductive approach. Finally, quantitative and qualitative results were merged. The findings indicated that almost all instructors and cadets had awareness about active learning. Sometimes instructors are practicing active learning but the level of their practice was not satisfactory. Large class size, lack of administrative support, lack of materials or equipment needed to support active learning and cadets lack of interest on active learning methods were rated as the factors that have been negatively affecting the practice of active learning in Amhara Region Police College. Thus, it is critically important that instructors should be committed to discharge their roles to exercise active learning, the administration of the college and other stakeholders should design and implement a mechanism to monitor the practice of active learning, the concerned bodies of the college should design different mechanisms to avoid these problems by appropriately allocating the time, revising crowded materials and avoiding large and unnecessary contents to practice active learning in Amhara Region Police College. Keywords: Active learning, challenges, Amhara Region Police College, cadets DOI: 10.7176/JEP/12-1-02 Publication date: January 31 st 2021

Machine learning applications that are implemented with spike-based computation model, e.g., Spiking Neural Network (SNN), have a great potential to lower the energy consumption when they are executed on a neuromorphic hardware. However, compiling and mapping an SNN to the hardware is challenging, especially when compute and storage resources of the hardware (viz. crossbar) need to be shared among the neurons and synapses of the SNN. We propose an approach to analyze and compile SNNs on a resource-constrained neuromorphic hardware, providing guarantee on key performance metrics such as execution time and throughput. Our approach makes the following three key contributions. First, we propose a greedy technique to partition an SNN into clusters of neurons and synapses such that each cluster can fit on to the resources of a crossbar. Second, we exploit the rich semantics and expressiveness of Synchronous Dataflow Graphs (SDFGs) to represent a clustered SNN and analyze its performance using Max-Plus Algebra, considering the available compute and storage capacities, buffer sizes, and communication bandwidth. Third, we propose a self-timed execution-based fast technique to compile and admit SNN-based applications to a neuromorphic hardware at run-time, adapting dynamically to the available resources on the hardware. We evaluate our approach with standard SNN-based applications and demonstrate a significant performance improvement compared to current practices.

Spiking neural network (SNN) has drawn research interests as it mimics dynamic activities of human brain and has the potential to perform real-time cognitive tasks. However, latency, throughput and flexibility of existing hardware implemented SNNs are limited. The conventional rate coding is inefficient in terms of accuracy and latency. Oversimplified SNN models adopted by neuromorphic hardware discard characteristics such as neuron dynamics and filter effects etc., which are critical for neural information processing. Recent research advancements show that the potential of SNN can be better utilized by moving beyond rate-based model and considering temporal information embedded in the spike sequences. However, these works employ complex biologically realistic SNN models, posing challenges to hardware complexity. Furthermore, most existing neuromorphic hardware are developed for specific SNN models, or aiming at replicating biological behaviors. There is a lack of general methodology for SNN design optimization. Novel hardware architecture and systematic optimization techniques are required for efficient FPGA implementation and support flexible SNN models. To address above issues, in this work we proposed a holistic optimization framework for encoder, model, and architecture design of FPGA based neuromorphic hardware. We present an efficient neural coding scheme and training algorithm, which can optimize encoder parameters to enable fast inference. A flexible and hardware-friendly model is proposed, in which SNNs are represented as a network of Infinite Impulse Response (IIR) filters. Finally, an end-to-end framework is developed to optimize and deploy FPGA implementation. Experimental results show our work achieves state-of-the-art accuracy in various classification tasks, and outperforms various platforms including CPU, GPU and dedicated neuromorphic processors in terms of latency and throughput.