• ETRI Journal
• /
• v.41 no.2
• /
• pp.242-253
• /
• 2019

We devise a layer-wise hint training method to improve the existing hint-based knowledge distillation (KD) training approach, which is employed for knowledge transfer in a teacher-student framework using a residual network (ResNet). To achieve this objective, the proposed method first iteratively trains the student ResNet and incrementally employs hint-based information extracted from the pretrained teacher ResNet containing several hint and guided layers. Next, typical softening factor-based KD training is performed using the previously estimated hint-based information. We compare the recognition accuracy of the proposed approach with that of KD training without hints, hint-based KD training, and ResNet-based layer-wise pretraining using reliable datasets, including CIFAR-10, CIFAR-100, and MNIST. When using the selected multiple hint-based information items and their layer-wise transfer in the proposed method, the trained student ResNet more accurately reflects the pretrained teacher ResNet's rich information than the baseline training methods, for all the benchmark datasets we consider in this study.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.209-215
• /
• 2022

This paper proposes a novel approach for training an unsupervised depth estimation algorithm. The objective of unsupervised depth estimation is to estimate pixel-wise distances from camera without external supervision. While most previous works focus on model architectures, loss functions, and masking methods for considering dynamic objects, this paper focuses on the training framework to effectively use depth cue. The main loss function of unsupervised depth estimation algorithms is known as the photometric error. In this paper, we claim that direct depth cue is more effective than the photometric error. To obtain the direct depth cue, we adopt the technique of knowledge distillation which is a teacher-student learning framework. We train a teacher network based on a previous unsupervised method, and its depth predictions are utilized as pseudo labels. The pseudo labels are employed to train a student network. In experiments, our proposed algorithm shows a comparable performance with the state-of-the-art algorithm, and we demonstrate that our teacher-student framework is effective in the problem of unsupervised depth estimation.

• Journal of Korean Elementary Science Education
• /
• v.36 no.3
• /
• pp.227-245
• /
• 2017

The purpose of this study was to explore the possibility of implementing 'responsive teaching (RT)' in elementary school science classrooms. A review of relevant literature yielded a tentative framework of RT which consisted of three characteristics of RT and example practices for each characteristic. The RT framework was used to analyze elementary science lessons on the topic of the transpiration in plant leaves. The data sources were audio recordings of three $5^{th}$ grade classrooms which included both the whole-class instruction and student group activities. The data were examined through collaboration between the teacher who had taught the lessons and a university-based science education researcher. It was revealed that the implementation of RT was limited when the teacher's intervention was focused on completing tasks; when it was out of the contexts of student activities; when the teacher provided earlier what students were supposed to find out by themselves; and when the teacher's comments were evaluation-centered. By contrast, the implementation of RT was made highly possible when the teacher's intervention induced an intellectual debate among students; when the teacher negotiated meanings with students; when the teacher connected what students shared to scientific knowledge; and when the teacher prompted students to solve a new problem. Implications about implementing and studying RT were discussed.

• Research in Mathematical Education
• /
• v.15 no.1
• /
• pp.59-68
• /
• 2011

This paper proposes a modified category framework derived from VAMP and VIMT projects for describing teachers' mathematical and pedagogical values, and examines the dialectical relations between values awareness/willingness and teaching, based on case studies of student teachers of secondary mathematics from a follow-up project of VIMT. The preliminary results show that student teachers would teach certain values depending on the awareness of values priority, willingness to teach, their teaching capabilities and classroom conditions. So, mathematics teacher educators should provide relevant courses to facilitate student teachers to be aware of their implicit values and be willing to enact these values, and to empower student teachers with the knowledge and experiences to teach the values.

• Research in Mathematical Education
• /
• v.22 no.2
• /
• pp.135-152
• /
• 2019

This conceptual paper proposes a conceptualization regarding teacher candidates' experiences as learners during instructional activities implemented by teacher educators in practice-based teacher education programs. We argue that the current learning cycle framework for teacher candidates to engage in core teaching practices does not fully address teacher candidates' own learning experiences as learners. To provide a rationale for our proposal, we examine the current conceptualization of learning to enact core practices and suggest the need for integrating teacher candidates' experiences into the current conceptualization. We also draw on research on figured worlds as an effort to conceptualize teacher candidates' experiences coming from multiple figured world. We present some examples from our own mathematics methods courses to illustrate how this newly proposed framework can be used in practice and share remaining questions for future research.

• Journal of the Korean earth science society
• /
• v.31 no.5
• /
• pp.521-530
• /
• 2010

This study aimed to explore how to characterize the earth science inquiry in schools in terms of science teaching interaction and constructivist teaching practice. The constructivist teaching practices were analyzed with Reformed Teaching Observation Protocol (RTOP) in three aspects including (1) student oriented class implementation, (2) subject knowledge and representation, and (3) classroom communication. Fourteen earth science classes were observed and scored with RTOP. The class was evaluated to be transitional stage in terms of constructivist teaching, e.g., moving toward student-centered teaching practice. Especially, Korean teachers tend to lean their classes more on propositional knowledge than procedural knowledge. To interpret science teaching interactions, an earth science teacher with a RTOP top rank was selected. Her class was then videotaped for detailed analysis. I adopted the analytical framework of communicative approaches and discourse patterns among the five aspects of interactions presented by Mortimer and Scott (2003). It was found that this earth science teacher used more authoritative patterns than the dialogic. In addition, she used IRE discourse pattern more frequently. Interestingly, teachers interacted with their students more frequently in the form of repeated (or IRE chain pattern), that is IRFRF (teacher initiation-student response-teacher feedback-student response-teacher feedback) in the context of dialogic communicative approaches, while simple IRE occurred in an authoritative approach. In earth science classrooms, typical interaction may well be constructed in the form of IRFRF chains to allow students free conjectures and abduction.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.35-41
• /
• 2017

In this paper, we analyze the performance of the recently introduced Hint-knowledge distillation (KD) training approach based on the teacher-student framework for knowledge distillation and knowledge transfer. As a deep neural network (DNN) considered in this paper, the deep residual network (ResNet), which is currently regarded as the latest DNN, is used for the teacher-student framework. Therefore, when implementing the Hint-KD training, we investigate the impact on the weight of KD information based on the soften factor in terms of classification accuracy using the widely used open deep learning frameworks, Caffe. As a results, it can be seen that the recognition accuracy of the student model is improved when the fixed value of the KD information is maintained rather than the gradual decrease of the KD information during training.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.483-488
• /
• 2018

Far field input utterance is one of the major causes of performance degradation of speaker verification systems. In this study, we used teacher student learning framework to compensate for the performance degradation caused by far field utterances. Teacher student learning refers to training the student deep neural network in possible performance degradation condition using the teacher deep neural network trained without such condition. In this study, we use the teacher network trained with near distance utterances to train the student network with far distance utterances. However, through experiments, it was found that performance of near distance utterances were deteriorated. To avoid such phenomenon, we proposed techniques that use trained teacher network as initialization of student network and training the student network using both near and far field utterances. Experiments were conducted using deep neural networks that input raw waveforms of 4-channel utterances recorded in both near and far distance. Results show the equal error rate of near and far-field utterances respectively, 2.55 % / 2.8 % without teacher student learning, 9.75 % / 1.8 % for conventional teacher student learning, and 2.5 % / 2.7 % with proposed techniques.

• Journal of the Korean Chemical Society
• /
• v.59 no.6
• /
• pp.520-532
• /
• 2015

The purposes of this study were to examine what kinds of educational activities were carried out during the practice teaching based on CoRe and to identify the role of CoRe and its influence on the development of expertise of student teachers. This study was performed as qualitative case study. The subjects of this study were one practice supervisor teacher and two student teachers. Data were collected through recording CoRe discussion process, student teachers' instructional scene, and semi-constructed interview, and analyzed by an inductive method. Student teachers noticed their own misconceptions, and clarified the concepts based on CoRe during the discussion with supervisor teacher. They also supplemented their lack of knowledge and made up new strategies through the process of sharing their ideas. During the discussion, the supervisor teacher conveyed his teaching experience based on his own orientations toward science teaching. In this course, CoRe plays roles as follows. Firstly, CoRe played a role as guiding supervisor teacher's coaching process. Secondly, CoRe helped for the supervisor teacher to recognize their own PCK. Thirdly, CoRe served as a tool of helping their communication. In turn CoRe proved to be a useful frame for teaching student teachers during practice teaching. Student teachers were provided with a useful framework for preparing lessons by developing CoRe for the topic they teach. Developing CoRe with supervisor teacher at the planning stage of lessons enhenced student-teachers' subject matter knowledge and their PCK including knowledge of science curricula and knowledge of student's understanding of science. Also student teachers understood the components of PCK and experienced the positive understanding toward students, teaching activities, and themselves as a science teacher.

• Journal of Korean Library and Information Science Society
• /
• v.39 no.2
• /
• pp.449-467
• /
• 2008

In this study, collaboration of teacher librarians and subject teachers in school libraries has been investigated(tried, attempted, suggested) in order to improve the information literacy. The effective teaching-learning can be conducted by extending student's roles, which are essential elements in school education. Above all, the model. focused on direct exchange of knowledges in communications between teachers and students has been suggested with consideration of content knowledge, pedagogical knowledge, and technological knowledge.