scholarly journals A strategy learning model for autonomous agents based on classification

2015 ◽  
Vol 25 (3) ◽  
pp. 471-482 ◽  
Author(s):  
Bartłomiej Śnieżyński
Keyword(s):  
Reinforcement Learning ◽  
Supervised Learning ◽  
Learning Process ◽  
Autonomous Agents ◽  
Good Alternative ◽  
Learning Model ◽  
Learning Method ◽  
Complex Environments ◽  
Agent Based ◽  
Proposed Model

AbstractIn this paper we propose a strategy learning model for autonomous agents based on classification. In the literature, the most commonly used learning method in agent-based systems is reinforcement learning. In our opinion, classification can be considered a good alternative. This type of supervised learning can be used to generate a classifier that allows the agent to choose an appropriate action for execution. Experimental results show that this model can be successfully applied for strategy generation even if rewards are delayed. We compare the efficiency of the proposed model and reinforcement learning using the farmer-pest domain and configurations of various complexity. In complex environments, supervised learning can improve the performance of agents much faster that reinforcement learning. If an appropriate knowledge representation is used, the learned knowledge may be analyzed by humans, which allows tracking the learning process

scholarly journals PENGEMBANGAN MODEL PEMBELAJARAN PEMERANAN BERORIENTASI TEKNIK CS PADA TEATER TRADISI

2018 ◽  
Vol 14 (25) ◽  
pp. 49-58
Author(s):  
Moh mujib Alfirdaus
Keyword(s):  
Learning Process ◽  
Learning Model ◽  
Learning Method ◽  
Academic Field ◽  
Efficient Learning ◽  
Rule Out

This learning model is the author's attempt to develop acting method in traditional theater through the Stanislavski's technique, although the need for theater tradition performances and theater conventional realism performance is different. During this time the method of play in the theater tradition is still spontaneous, but the method of acting on the theater tradition must be measurable and can be studied in the academic field, hence, the author develops acting methods based on Stanislavski's technique as a reference in learning. An actor is a student for nature and pupil for anyone as long as the knowledge he earned is useful to develops his acting creativity. Therefore this Stanislavski's method becomes very influential to train the actor's intelligence, despite his need for traditional theater. Why is Stanislavski's method becoming important to be learned by actor candidate ?. Because the analysis used by Stanislavski's method is still very logical and reasonable, it did not rule out the effects of int elligence for anyone who  applied  it.  This  circumstance emphasizing  the  importance of Developing  Stanilavski's technique-oriented Learning Model on Traditional Theater. In order for candidates who will perform for traditional and modern show, are expected to be ready with all the acting devices to employ. Therefore, this learning method need to be applied, especially in STKW Surabaya. The purpose of this research is developing a learning model for acting in the theater tradition. This research carried out  by producing several outcome. First, a handbook of Stanislavski's method learning model for student. Second, a lecturer's handbook for an effective and efficient learning process

scholarly journals Unsupervised learning and clustered connectivity enhance reinforcement learning in spiking neural networks

2020 ◽  
Author(s):  
Philipp Weidel ◽  
Renato Duarte ◽  
Abigail Morrison
Keyword(s):  
Reinforcement Learning ◽  
Unsupervised Learning ◽  
Activity Patterns ◽  
Receptive Fields ◽  
Place Cells ◽  
Spiking Neural Networks ◽  
Complex Environments ◽  
Proposed Model ◽  
Clustered Network ◽  
Better Than

ABSTRACTReinforcement learning is a learning paradigm that can account for how organisms learn to adapt their behavior in complex environments with sparse rewards. However, implementations in spiking neuronal networks typically rely on input architectures involving place cells or receptive fields. This is problematic, as such approaches either scale badly as the environment grows in size or complexity, or presuppose knowledge on how the environment should be partitioned. Here, we propose a learning architecture that combines unsupervised learning on the input projections with clustered connectivity within the representation layer. This combination allows input features to be mapped to clusters; thus the network self-organizes to produce task-relevant activity patterns that can serve as the basis for reinforcement learning on the output projections. On the basis of the MNIST and Mountain Car tasks, we show that our proposed model performs better than either a comparable unclustered network or a clustered network with static input projections. We conclude that the combination of unsupervised learning and clustered connectivity provides a generic representational substrate suitable for further computation.

scholarly journals Unsupervised Learning and Clustered Connectivity Enhance Reinforcement Learning in Spiking Neural Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Philipp Weidel ◽  
Renato Duarte ◽  
Abigail Morrison
Keyword(s):  
Reinforcement Learning ◽  
Unsupervised Learning ◽  
Ad Hoc ◽  
Activity Patterns ◽  
Receptive Fields ◽  
Complex Environments ◽  
Self Organized ◽  
Proposed Model ◽  
The Brain ◽  
Clustered Network

Reinforcement learning is a paradigm that can account for how organisms learn to adapt their behavior in complex environments with sparse rewards. To partition an environment into discrete states, implementations in spiking neuronal networks typically rely on input architectures involving place cells or receptive fields specified ad hoc by the researcher. This is problematic as a model for how an organism can learn appropriate behavioral sequences in unknown environments, as it fails to account for the unsupervised and self-organized nature of the required representations. Additionally, this approach presupposes knowledge on the part of the researcher on how the environment should be partitioned and represented and scales poorly with the size or complexity of the environment. To address these issues and gain insights into how the brain generates its own task-relevant mappings, we propose a learning architecture that combines unsupervised learning on the input projections with biologically motivated clustered connectivity within the representation layer. This combination allows input features to be mapped to clusters; thus the network self-organizes to produce clearly distinguishable activity patterns that can serve as the basis for reinforcement learning on the output projections. On the basis of the MNIST and Mountain Car tasks, we show that our proposed model performs better than either a comparable unclustered network or a clustered network with static input projections. We conclude that the combination of unsupervised learning and clustered connectivity provides a generic representational substrate suitable for further computation.

Penerapan Metode Probing Promting Pada Mata Pelajaran Fiqih Dalam Meningkatkan Motivasi Belajar Siswa Kelas VIII MTs Tarbiyah Waladiyah Pulau Banyak

2019 ◽  
Vol 1 (1) ◽  
pp. 103-128
Author(s):  
Ahmad Fuadi ◽  
Usmaidar Usmaidar ◽  
Yuliana Yuliana
Keyword(s):  
Learning Process ◽  
Learning Model ◽  
Learning Motivation ◽  
Learning Method ◽  
Thought Process ◽  
Learning Achievement ◽  
New Knowledge ◽  
Question And Answer ◽  
Definition Of

    Ahmad Fuadi1 , Usmaidar2, Yuliana3 Sekolah Tinggi Agama Islam Jam’iyah Mahmudiyah Tanjung Pura1,2,3 Email : [email protected] , [email protected]     ABSTRACT The learning method of Probing Promting is "Learning by means of the teacher presenting a series of statements that are guiding and digging so that a thought process occurs which links each student's knowledge and experience with the new knowledge that is being learned. With this learning model the question and answer process is carried out by randomly assigning students so that each student inevitably has to participate actively, students cannot avoid the learning process, at any time they can be involved in the question and answer process. With this learning model the question and answer process is carried out by randomly assigning students so that each student inevitably has to participate actively, students cannot avoid the learning process, at any time they can be involved in the question and answer process. The definition of motivation is the change in energy in a person which is marked by the emergence of feelings and is preceded by a response to a goal. A series of activities carried out by each party or individual is actually motivated by something or what is generally called motivation. Motivation is what encourages them to carry out an activity or job. it is this motivation that a person will be more successful in a lesson. So, motivation will always determine the intensity of learning efforts for students. And it needs to be emphasized that motivation is closely related to goals. To support the interest in learning for each individual, there must be motivation in learning, because that motivation will move the person to do something, in this case, learning. With diligent effort and primarily based on motivation, someone who learns will be able to produce good achievements. The intensity of a student's motivation will greatly determine the level of learning achievement. Keywords: Probing Promting Method, Learning Motivation, Fiqh Lessons

scholarly journals A Method of Personalized Driving Decision for Smart Car Based on Deep Reinforcement Learning

Information ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 295 ◽  
Author(s):  
Xinpeng Wang ◽  
Chaozhong Wu ◽  
Jie Xue ◽  
Zhijun Chen
Keyword(s):  
Reinforcement Learning ◽  
Decision Model ◽  
Gradient Algorithm ◽  
Learning Goals ◽  
Learning Method ◽  
Automatic Driving ◽  
Proposed Model ◽  
Policy Gradient ◽  
Self Learning ◽  
Better Than

To date, automatic driving technology has become a hotspot in academia. It is necessary to provide a personalization of automatic driving decision for each passenger. The purpose of this paper is to propose a self-learning method for personalized driving decisions. First, collect and analyze driving data from different drivers to set learning goals. Then, Deep Deterministic Policy Gradient algorithm is utilized to design a driving decision system. Furthermore, personalized factors are introduced for some observed parameters to build a personalized driving decision model. Finally, compare the proposed method with classic Deep Reinforcement Learning algorithms. The results show that the performance of the personalized driving decision model is better than the classic algorithms, and it is similar to the manual driving situation. Therefore, the proposed model can effectively learn the human-like personalized driving decisions of different drivers for structured road. Based on this model, the smart car can accomplish personalized driving.

scholarly journals Urgensi Model Pembelajaran Interaktif dalam Meningkatkan Prestasi dan Motivasi Belajar Siswa dalam Mata Pelajaran Pendidikan Agama Islam

2021 ◽  
Vol 15 (1) ◽  
pp. 1
Author(s):  
Fauzi Rahmanul Hakim
Keyword(s):  
Religious Education ◽  
Learning Process ◽  
Learning Model ◽  
Islamic Education ◽  
Learning Problems ◽  
Learning Method ◽  
Learning Models ◽  
Literature Study ◽  
Study Approach ◽  
Left Behind

In learning Islamic Religious Education (PAI) students need a learning model that is appropriate and precise in its characteristics. Learning model is termed by interpreting a broader scope than the learning method or strategy. Therefore, the learning model can be interpreted as planning which is used as a reference or rule in the learning process carried out in the classroom and can be a determinant of learning equipment such as teaching materials, books, curriculum, and so on. So it can be said that the learning model is a directional framework from the educator for the teaching process. This research tries to present an overview of the learning problems of an interactive model in the practice of Islamic education. Islamic education is now faced with various kinds of challenges, demands and needs that have never existed before. So it is not enough with just one learning model, it takes innovation in the renewal of the learning model that is tailored to the system needs, curriculum, human resource competencies, infrastructure, and others. If not, then Islamic education in practice will be increasingly left behind because it becomes a problem of learning models that do not adapt to developments. This research uses a literature study approach, data collection through text studies, then the data obtained is analyzed using content analysis. This method intends to analyze the problems of interactive learning in Islamic education practices. So it becomes a solution if the urgency learning model is made into a good innovation from its weaknesses and strengths. Because the learning process of students will be considered more effective if students after learning can find out something that was not previously known. So, learning achievement will change for the better with a change in new behavior in the level of reason, knowledge, thinking or advancement of physical potential.

scholarly journals UPAYA PENINGKATAN HASIL BELAJAR IPS KELAS II SD NEGERI II KEMLOKO DENGAN MENGGUNAKAN MODEL MAKE A MATCH

2017 ◽  
Vol 1 (2) ◽  
pp. 113
Author(s):  
Dwi Wulandari
Keyword(s):  
Action Research ◽  
Learning Outcomes ◽  
Learning Process ◽  
Learning Outcome ◽  
Learning Model ◽  
Class Action ◽  
Learning Activities ◽  
Learning Method ◽  
Research Model ◽  
Interesting Learning

IPS learning process that occurs at SDN II Kemloko 2nd grade class has not been achieved its satisfactory. This is due to the way the teachers teach which is still in mediocre level, in a way of providing the students with interesting learning method and interesting models that may make students happy to follow the learning activities. By the result, the students’ learning outcomes for the 2nd grade class at SDN II Kemloko still below the pre-determined score, commonly known as KKM. In order to make this condition better, the researchers are triggered to conduct a research by implementing a Class Action Research (PTK), by referring to a research model raised by Thursday and Mc. Taggart. That research model proposes 4 important stages, which are (1) preparation / planning, (2) implementation of the action, (3) observation / observation, (4) reflection. In this classroom action research, the researchers implement a learning model, which is Make a Match. Afterwards, the result shows that the 2nd grade students can experience learning outcome. It turned out that after using this model of Make a Match, there is a significant improvement. The results obtained from cycle 1 portraying a number of 17 students shows that there are 9 students who successfully accomplish the task, which is equivalent with 52.94%, and the rest of the students, which are 8 students, are not able to accomplish the task, equivalent with 47.06%. Further, the second cycle presents that the students who pass the results are 10 students with a percentage of 58.82%, while the unaccomplished ones are 7 students with a percentage of 41.18%. According to the results, the result shows that the accomplished number of students is above the average. It is strongly suggested that others may implement the learning model of Make a Match, particularly teachers.

scholarly journals Penerapan Pendidikan Lingkungan Hidup Di Perguruan Tinggi Dengan Model Outdoor Learning

2018 ◽  
Vol 1 (3) ◽  
pp. 77
Author(s):  
Muhammad Ali ◽  
Muhammad Ardi ◽  
Suradi Tahmir
Keyword(s):  
Higher Education ◽  
Learning Process ◽  
Learning Model ◽  
Outdoor Learning ◽  
Learning Method ◽  
Learning Materials ◽  
Environmental Learning ◽  
Advantages And Disadvantages ◽  
Surrounding Environment ◽  
General Goals

environmental learning aims that students have concern for the surrounding environment. The learning model of environmental learning (EL) described in this article applies the outdoor learning method. Learning materials presented to students are arranged by involving the surrounding environment. This means that learning can be done not only in classrooms, but also outside the classroom in order for students to be more comfortable and active in the learning process. the initial ability of students needs to be considered in the learning process because it affects the ability of students to follow the next learning process. This article describes the meaning, goals and benefits, advantages and disadvantages and the stages of the method of outdoor learning. So that it can be concluded that higher education is education in higher education that has several general goals / principles where knowledge (knowledge) is created, used continuously and a place of search for knowledge, solving various problems, where to criticize the works produced, or as the place for the formation and development of student character to become a student who has high reasoning, sharp and broad analysis. Especially in environment-based learning developed so that students gain more experience related to the surrounding environment.         

scholarly journals Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

2020 ◽  
Author(s):  
Gang Yu ◽  
Ting Xie ◽  
Chao Xu ◽  
Xing-Hua Shi ◽  
Chong Wu ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
Supervised Learning ◽  
The United States ◽  
Learning Model ◽  
Learning Method ◽  
Data Set ◽  
Patient Level ◽  
Significant Difference ◽  
Better Than

AbstractPurposesThe machine-assisted recognition of colorectal cancer using pathological images has been mainly focused on supervised learning approaches that suffer from a significant bottleneck of requiring a large number of labeled training images. The process of generating high quality image labels is time-consuming, labor-intensive, and thus lags behind the quick accumulation of pathological images. We hypothesize that semi-supervised deep learning, a method that leverages a small number of labeled images together with a large quantity of unlabeled images, can provide a powerful alternative strategy for colorectal cancer recognition.MethodWe proposed semi-supervised classifiers based on deep learning that provide pathological predictions at both patch-level and the level of whole slide image (WSI). First, we developed a semi-supervised deep learning framework based on the mean teacher method, to predict the cancer probability of an individual patch by utilizing patch-level data generated by dividing a WSI into many patches. Second, we developed a patient-level method utilizing a cluster-based and positive sensitivity strategy on WSIs to predict whether the WSI or the associated patient has cancer or not. We demonstrated the general utility of the semi-supervised learning method for colorectal cancer prediction utilizing a large data set (13,111 WSIs from 8,803 subjects) gathered from 13 centers across China, the United States and Germany. On this data set, we compared the performances of our proposed semi-supervised learning method with those from the prevailing supervised learning methods and six professional pathologists.ResultsOur results confirmed that semi-supervised learning model overperformed supervised learning models when a small portion of massive data was labeled, and performed as well as a supervised learning model when using massive labeled data. Specifically, when a small amount of training patches (~3,150) was labeled, the proposed semi-supervised learning model plus ~40,950 unlabeled patches performed better than the supervised learning model (AUC: 0.90 ± 0.06 vs. 0.84 ± 0.07,P value = 0.02). When more labeled training patches (~6,300) were available, the semi-supervised learning model plus ~37,800 unlabeled patches still performed significantly better than a supervised learning model (AUC: 0.98 ± 0.01vs. 0.92 ± 0.04, P value = 0.0004), and its performance had no significant difference compared with a supervised learning model trained on massive labeled patches (~44,100) (AUC: 0.98 ± 0.01 vs. 0.987 ± 0.01, P value = 0.134). Through extensive patient-level testing of 12,183 WSIs in 12 centers, we found no significant difference on patient-level diagnoses between the semi-supervised learning model (~6,300 labeled, ~37,800 unlabeled training patches) and a supervised learning model (~44,100 labeled training patches) (average AUC: 97.40% vs. 97.96%, P value = 0.117). Moreover, the diagnosis accuracy of the semi-supervised learning model was close to that of human pathologists (average AUC: 97.17% vs. 96.91%).ConclusionsWe reported that semi-supervised learning can achieve excellent performance at patch-level and patient-level diagnoses for colorectal cancer through a multi-center study. This finding is particularly useful since massive labeled data are usually not readily available. We demonstrated that our newly proposed semi-supervised learning method can accurately predict colorectal cancer that matched the average accuracy of pathologists. We thus suggested that semi-supervised learning has great potentials to build artificial intelligence (AI) platforms for medical sciences and clinical practices including pathological diagnosis. These new platforms will dramatically reduce the cost and the number of labeled data required for training, which in turn will allow for broader adoptions of AI-empowered systems for cancer image analyses.

scholarly journals Learn to Steer through Deep Reinforcement Learning

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3650 ◽  
Author(s):  
Keyu Wu ◽  
Mahdi Esfahani ◽  
Shenghai Yuan ◽  
Han Wang
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
High Efficiency ◽  
Feature Representation ◽  
Fine Tuning ◽  
Computational Time ◽  
Complex Environments ◽  
Learning Efficiency ◽  
Depth Images ◽  
Proposed Model

It is crucial for robots to autonomously steer in complex environments safely without colliding with any obstacles. Compared to conventional methods, deep reinforcement learning-based methods are able to learn from past experiences automatically and enhance the generalization capability to cope with unseen circumstances. Therefore, we propose an end-to-end deep reinforcement learning algorithm in this paper to improve the performance of autonomous steering in complex environments. By embedding a branching noisy dueling architecture, the proposed model is capable of deriving steering commands directly from raw depth images with high efficiency. Specifically, our learning-based approach extracts the feature representation from depth inputs through convolutional neural networks and maps it to both linear and angular velocity commands simultaneously through different streams of the network. Moreover, the training framework is also meticulously designed to improve the learning efficiency and effectiveness. It is worth noting that the developed system is readily transferable from virtual training scenarios to real-world deployment without any fine-tuning by utilizing depth images. The proposed method is evaluated and compared with a series of baseline methods in various virtual environments. Experimental results demonstrate the superiority of the proposed model in terms of average reward, learning efficiency, success rate as well as computational time. Moreover, a variety of real-world experiments are also conducted which reveal the high adaptability of our model to both static and dynamic obstacle-cluttered environments. A video of our experiments is available at https://youtu.be/yixnmFXIKf4 and http://v.youku.com/vshow/idXMzg1ODYwMzM5Ng.

Sign in / Sign up

Export Citation Format

Share Document