ترغب بنشر مسار تعليمي؟ اضغط هنا

Iterative Machine Teaching without Teachers

116   0   0.0 ( 0 )
 نشر من قبل Mingzhe Yang
 تاريخ النشر 2020
والبحث باللغة English




اسأل ChatGPT حول البحث

Iterative machine teaching is a method for selecting an optimal teaching example that enables a student to efficiently learn a target concept at each iteration. Existing studies on iterative machine teaching are based on supervised machine learning and assume that there are teachers who know the true answers of all teaching examples. In this study, we consider an unsupervised case where such teachers do not exist; that is, we cannot access the true answer of any teaching example. Students are given a teaching example at each iteration, but there is no guarantee if the corresponding label is correct. Recent studies on crowdsourcing have developed methods for estimating the true answers from crowdsourcing responses. In this study, we apply these to iterative machine teaching for estimating the true labels of teaching examples along with student models that are used for teaching. Our method supports the collaborative learning of students without teachers. The experimental results show that the teaching performance of our method is particularly effective for low-level students in particular.



قيم البحث

اقرأ أيضاً

95 - Weiyang Liu , Bo Dai , Xingguo Li 2017
In this paper, we make an important step towards the black-box machine teaching by considering the cross-space machine teaching, where the teacher and the learner use different feature representations and the teacher can not fully observe the learner s model. In such scenario, we study how the teacher is still able to teach the learner to achieve faster convergence rate than the traditional passive learning. We propose an active teacher model that can actively query the learner (i.e., make the learner take exams) for estimating the learners status and provably guide the learner to achieve faster convergence. The sample complexities for both teaching and query are provided. In the experiments, we compare the proposed active teacher with the omniscient teacher and verify the effectiveness of the active teacher model.
An educator who is also known as a lecturer in the university system has three main areas of focus, which include learning that is helping students to acquire knowledge, competence and virtue, research, implying developing new knowledge, breaking new grounds and community service, by focusing on applying the knowledge to real life situations to improve life and living conditions of the society. As the worlds geographical boundaries keep getting redefined in the context of a global village, the constituency of teachers keeps getting redefined as well. This essay aims to address issues about modern constituent and platform of teachers in Nigeria for service delivery in the context of a globalised world. It also focuses on how to reach out to these new set of communities brought about by globalisation to remain relevant, effective and efficient alongside their perceived challenges and possible solutions in Nigerian context.
In this paper we try to organize machine teaching as a coherent set of ideas. Each idea is presented as varying along a dimension. The collection of dimensions then form the problem space of machine teaching, such that existing teaching problems can be characterized in this space. We hope this organization allows us to gain deeper understanding of individual teaching problems, discover connections among them, and identify gaps in the field.
Machine teaching is an inverse problem of machine learning that aims at steering the student learner towards its target hypothesis, in which the teacher has already known the students learning parameters. Previous studies on machine teaching focused on balancing the teaching risk and cost to find those best teaching examples deriving the student model. This optimization solver is in general ineffective when the student learner does not disclose any cue of the learning parameters. To supervise such a teaching scenario, this paper presents a distribution matching-based machine teaching strategy. Specifically, this strategy backwardly and iteratively performs the halving operation on the teaching cost to find a desired teaching set. Technically, our strategy can be expressed as a cost-controlled optimization process that finds the optimal teaching examples without further exploring in the parameter distribution of the student learner. Then, given any a limited teaching cost, the training examples will be closed-form. Theoretical analysis and experiment results demonstrate this strategy.
Successful teaching requires an assumption of how the learner learns - how the learner uses experiences from the world to update their internal states. We investigate what expectations people have about a learner when they teach them in an online man ner using rewards and punishment. We focus on a common reinforcement learning method, Q-learning, and examine what assumptions people have using a behavioral experiment. To do so, we first establish a normative standard, by formulating the problem as a machine teaching optimization problem. To solve the machine teaching optimization problem, we use a deep learning approximation method which simulates learners in the environment and learns to predict how feedback affects the learners internal states. What do people assume about a learners learning and discount rates when they teach them an idealized exploration-exploitation task? In a behavioral experiment, we find that people can teach the task to Q-learners in a relatively efficient and effective manner when the learner uses a small value for its discounting rate and a large value for its learning rate. However, they still are suboptimal. We also find that providing people with real-time updates of how possible feedback would affect the Q-learners internal states weakly helps them teach. Our results reveal how people teach using evaluative feedback and provide guidance for how engineers should design machine agents in a manner that is intuitive for people.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا