DeepAI AI Chat

Learning Simple Algorithms from Examples

11/23/2015

∙

by Wojciech Zaremba, et al.

∙

Facebook

∙

∙

We present an approach for learning simple algorithms such as copying, multi-digit addition and single digit multiplication directly from examples. Our framework consists of a set of interfaces, accessed by a controller. Typical interfaces are 1-D tapes or 2-D grids that hold the input and output data. For the controller, we explore a range of neural network-based models which vary in their ability to abstract the underlying algorithm from training instances and generalize to test examples with many thousands of digits. The controller is trained using Q-learning with several enhancements and we show that the bottleneck is in the capabilities of the controller rather than in the search incurred by Q-learning.

Wojciech Zaremba
27 publications
Tomas Mikolov
31 publications
Armand Joulin
70 publications
Rob Fergus
48 publications

∙ 02/27/2020

Towards Modular Algorithm Induction

We present a modular neural network architecture Main that learns algori...

0 Daniel A. Abolafia, et al. ∙

∙ 11/30/2003

Hybrid LQG-Neural Controller for Inverted Pendulum System

The paper presents a hybrid system controller, incorporating a neural an...

0 E. S. Sazonov, et al. ∙

∙ 06/19/2020

Learning Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory

We present the first approach for learning – from a single trajectory – ...

0 Lenart Treven, et al. ∙

∙ 05/04/2015

Reinforcement Learning Neural Turing Machines - Revised

The Neural Turing Machine (NTM) is more expressive than all previously c...

0 Wojciech Zaremba, et al. ∙

∙ 12/07/2020

Development of Autonomous Quadcopter

The main objective of this work is demonstrated through two main aspects...

0 Mohammad Al-Fetyani, et al. ∙

∙ 08/14/2019

Heuristic Dynamic Programming for Adaptive Virtual Synchronous Generators

In this paper a neural network heuristic dynamic programing (HDP) is use...

0 Sepehr Saadatmand, et al. ∙

∙ 05/13/2022

Robustness of Control Design via Bayesian Learning

In the realm of supervised learning, Bayesian learning has shown robust ...

0 Nardos Ayele Ashenafi, et al. ∙

Code Repositories

algorithm-learning

None

view repo

learningSimpleAlgorithms

We present an approach for learning simple algorithms such as copying, multi-digit addition and single digit multiplication directly from examples. Our framework consists of a set of interfaces, accessed by a controller. Typical interfaces are 1-D tapes or 2-D grids that hold the input and output data. For the controller, we explore a range of neural network-based models which vary in their ability to abstract the underlying algorithm from training instances and generalize to test examples with

view repo

zaremba-learning-simple-algorithms

A Python implementation of Zaremba's "Learning Simple Algorithms from Examples" work.

view repo