Know Thy Student: Interactive Learning with Gaussian Processes

04/26/2022
by   Rose E. Wang, et al.
5

Learning often involves interaction between multiple agents. Human teacher-student settings best illustrate how interactions result in efficient knowledge passing where the teacher constructs a curriculum based on their students' abilities. Prior work in machine teaching studies how the teacher should construct optimal teaching datasets assuming the teacher knows everything about the student. However, in the real world, the teacher doesn't have complete information about the student. The teacher must interact and diagnose the student, before teaching. Our work proposes a simple diagnosis algorithm which uses Gaussian processes for inferring student-related information, before constructing a teaching dataset. We apply this to two settings. One is where the student learns from scratch and the teacher must figure out the student's learning algorithm parameters, eg. the regularization parameters in ridge regression or support vector machines. Two is where the student has partially explored the environment and the teacher must figure out the important areas the student has not explored; we study this in the offline reinforcement learning setting where the teacher must provide demonstrations to the student and avoid sending redundant trajectories. Our experiments highlight the importance of diagosing before teaching and demonstrate how students can learn more efficiently with the help of an interactive teacher. We conclude by outlining where diagnosing combined with teaching would be more desirable than passive learning.

READ FULL TEXT

page 2

page 6

page 7

page 11

page 12

page 13

page 14

page 15

research
03/11/2021

Learning by Teaching, with Application to Neural Architecture Search

In human learning, an effective skill in improving learning outcomes is ...
research
04/28/2015

Becoming the Expert - Interactive Multi-Class Machine Teaching

Compared to machines, humans are extremely good at classifying images in...
research
03/17/2022

Natural Language Communication with a Teachable Agent

Conversational teachable agents offer a promising platform to support le...
research
02/28/2017

Scaffolding Networks: Incremental Learning and Teaching Through Questioning

We introduce a new paradigm of learning for reasoning, understanding, an...
research
09/22/2021

Predicting Stress in Remote Learning via Advanced Deep Learning Technologies

COVID-19 has driven most schools to remote learning through online meeti...
research
05/07/2020

How Peripheral Interactive Systems Can Support Teachers with Differentiated Instruction: Using FireFlies as a Probe

Teachers' response to the real-time needs of diverse learners in the cla...
research
10/26/2019

ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations

Learning from demonstrations is a popular tool for accelerating and redu...

Please sign up or login with your details

Forgot password? Click here to reset