The Fast and the Flexible: training neural networks to learn to follow instructions from small data

09/17/2018
by   Rezka Leonandya, et al.
0

Learning to follow human instructions is a challenging task because while interpreting instructions requires discovering arbitrary algorithms, humans typically provide very few examples to learn from. For learning from this data to be possible, strong inductive biases are necessary. Work in the past has relied on hand-coded components or manually engineered features to provide such biases. In contrast, here we seek to establish whether this knowledge can be acquired automatically by a neural network system through a two phase training procedure: A (slow) offline learning stage where the network learns about the general structure of the task and a (fast) online adaptation phase where the network learns the language of a new given speaker. Controlled experiments show that when the network is exposed to familiar instructions but containing novel words, the model adapts very efficiently to the new vocabulary. Moreover, even for human speakers whose language usage can depart significantly from our artificial training language, our network can still make use of its automatically acquired inductive bias to learn to follow instructions more effectively.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/24/2023

Modeling rapid language learning by distilling Bayesian priors into artificial neural networks

Humans can learn languages from remarkably little experience. Developing...
research
04/25/2023

Pretrain on just structure: Understanding linguistic inductive biases using transfer learning

Both humans and transformer language models are able to learn language w...
research
02/19/2020

BB_Evac: Fast Location-Sensitive Behavior-Based Building Evacuation

Past work on evacuation planning assumes that evacuees will follow instr...
research
11/14/2017

Unified Pragmatic Models for Generating and Following Instructions

We extend models for both following and generating natural language inst...
research
01/14/2019

Human few-shot learning of compositional instructions

People learn in fast and flexible ways that have not been emulated by ma...
research
09/03/2020

Sparse Meta Networks for Sequential Adaptation and its Application to Adaptive Language Modelling

Training a deep neural network requires a large amount of single-task da...
research
09/27/2019

Playing Atari Ball Games with Hierarchical Reinforcement Learning

Human beings are particularly good at reasoning and inference from just ...

Please sign up or login with your details

Forgot password? Click here to reset