Large language models have recently shown a remarkable ability for few-shot learning, including patterns of algorithmic nature. However, it is still an open question to determine what kind of patterns these models can capture and how many examples they need in their prompts. We frame this question as a teaching problem with strong priors, and study whether language models can identify simple algorithmic concepts from small witness sets. In particular, we explore how several GPT architectures, program induction systems and humans perform in terms of the complexity of the concept and the number of additional examples, and how much their behaviour differs. This first joint analysis of language models and machine teaching can address key questions for artificial intelligence and machine learning, such as whether some strong priors, and Occam's razor in particular, can be distilled from data, making learning from a few examples possible.

In real-world applications of education, an effective teacher adaptively chooses the next example to teach based on the learner's current state. However, most existing work in algorithmic machine teachingfocuses on the batch setting, where adaptivity plays no role. In this paper, we study the case of teaching consistent, version space learners in an interactive setting. At any time step, the teacher provides an example, the learner performs an update, and the teacher observes the learner'snew state.

On the other hand, for goal-oriented tasks, humans create mental models of the environment for planning their actions to achieve their goals [1,2]. In AI systems, recent research has shown that usersformmentalmodelsoftheAI'sstateandbehaviour[ 3,4].

Weintroduceanaturalquantity,the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner is able to find a near-optimal policy using standard algorithms basedoninversereinforcement learning. Basedonthesefindings, we suggest a teaching scheme in which the expert can decrease the teaching risk by updating the learner's worldview, and thus ultimately enable her to find a near-optimalpolicy.

In human pedagogy, teachers and students can interact adaptively to maximize communication efficiency. Theteacher adjusts herteaching method fordifferent students, and the student, after getting familiar with the teacher's instruction mechanism,caninfertheteacher'sintentiontolearnfaster.

Neural Information Processing Systems http://nips.cc/

The emergence of the Internet-of-Things (IoT) sheds light on applying the machine teaching (MT) algorithms for online personalized education on home devices.

After that, the leaner solely and assiduously learns a target model from this dataset without further interaction.