Learning with Intelligent Teacher

Author(s):  
Vladimir Vapnik ◽  
Rauf Izmailov
Keyword(s):  
2021 ◽  
pp. 101-123
Author(s):  
Shengquan Yu ◽  
Yu Lu

2014 ◽  
Vol 1 (1) ◽  
Author(s):  
Herawati Susilo

<p>Improving the quality of teaching biology should continue to be done to establish a professional teacher of Biology and intelligent. This is not an easy thing to do as turning the hand because it requires the cooperation of all faculty in the Department of Biology that is expected from day to day also always improve professionalism . Biology lecturer and intelligent professional, who can develop his professionalism in accordance with the challenges of globalization and the dynamics of global education  will be a living example for students majoring in Biology. Biology teacher candidates who are prospective professional and intelligent teacher who always want to learn throughout life, literati Science and technology, mastering the English language, capable of carrying out classroom action research, writing scientific papers diligent, capable students according to the needs and development of the era, as well as having intelligence thinking. They are also expected to have the ability to constantly develop the ability, can produce intelligent action, which is done with full responsibility, and is able to be recognized by the public in carrying out their duties in the field of education and learning. One effort that can be done by lecturers Biology is biology of learning by presenting to increase the independence of students in learning, and develop metacognitive skills. Lecturer builder courses should be worked together to give its share in coaching students to become teachers of Biology is the professional and intelligent. Lecturers should be an example and role model for prospective Biology teachers who cultivated because of their tendency to learn students more or less the same as how they be taught in LPTK.</p>


Author(s):  
Chen Gong ◽  
Xiaojun Chang ◽  
Meng Fang ◽  
Jian Yang

Semi-Supervised Learning (SSL) is able to build reliable classifier with very scarce labeled examples by properly utilizing the abundant unlabeled examples. However, existing SSL algorithms often yield unsatisfactory performance due to the lack of supervision information. To address this issue, this paper formulates SSL as a Generalized Distillation (GD) problem, which treats existing SSL algorithm as a learner and introduces a teacher to guide the learner?s training process. Specifically, the intelligent teacher holds the privileged knowledge that ?explains? the training data but remains unknown to the learner, and the teacher should convey its rich knowledge to the imperfect learner through a specific teaching function. After that, the learner gains knowledge by ?imitating? the output of the teaching function under an optimization framework. Therefore, the learner in our algorithm learns from both the teacher and the training data, so its output can be substantially distilled and enhanced. By deriving the Rademacher complexity and error bounds of the proposed algorithm, the usefulness of the introduced teacher is theoretically demonstrated. The superiority of our algorithm to the related state-of-the-art methods has also been empirically demonstrated by the experiments on different datasets with various sources of privileged knowledge.


Sign in / Sign up

Export Citation Format

Share Document