Goal-Driven Sequential Data Abstraction

07/29/2019
by   Umar Riaz Muhammad, et al.
3

Automatic data abstraction is an important capability for both benchmarking machine intelligence and supporting summarization applications. In the former one asks whether a machine can `understand' enough about the meaning of input data to produce a meaningful but more compact abstraction. In the latter this capability is exploited for saving space or human time by summarizing the essence of input data. In this paper we study a general reinforcement learning based framework for learning to abstract sequential data in a goal-driven way. The ability to define different abstraction goals uniquely allows different aspects of the input data to be preserved according to the ultimate purpose of the abstraction. Our reinforcement learning objective does not require human-defined examples of ideal abstraction. Importantly our model processes the input sequence holistically without being constrained by the original input order. Our framework is also domain agnostic -- we demonstrate applications to sketch, video and text data and achieve promising results in all domains.

READ FULL TEXT

page 5

page 7

research
02/23/2023

Does Deep Learning Learn to Abstract? A Systematic Probing Framework

Abstraction is a desirable capability for deep learning models, which me...
research
04/13/2018

Learning Deep Sketch Abstraction

Human free-hand sketches have been studied in various contexts including...
research
02/10/2022

Abstraction for Deep Reinforcement Learning

We characterise the problem of abstraction in the context of deep reinfo...
research
03/01/2022

A Theory of Abstraction in Reinforcement Learning

Reinforcement learning defines the problem facing agents that learn to m...
research
09/11/2018

Abstraction Learning

There has been a gap between artificial intelligence and human intellige...
research
07/21/2020

What Programs Want: Automatic Inference of Input Data Specifications

Nowadays, as machine-learned software quickly permeates our society, we ...
research
11/09/2021

Learning Numerical Action Models from Noisy Input Data

This paper presents the PlanMiner-N algorithm, a domain learning techniq...

Please sign up or login with your details

Forgot password? Click here to reset