DeepAI AI Chat
Log In Sign Up

Learning Simple Algorithms from Examples

11/23/2015
by   Wojciech Zaremba, et al.
Facebook
0

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.

READ FULL TEXT
02/27/2020

Towards Modular Algorithm Induction

We present a modular neural network architecture Main that learns algori...
11/30/2003

Hybrid LQG-Neural Controller for Inverted Pendulum System

The paper presents a hybrid system controller, incorporating a neural an...
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 – ...
05/04/2015

Reinforcement Learning Neural Turing Machines - Revised

The Neural Turing Machine (NTM) is more expressive than all previously c...
12/07/2020

Development of Autonomous Quadcopter

The main objective of this work is demonstrated through two main aspects...
08/14/2019

Heuristic Dynamic Programming for Adaptive Virtual Synchronous Generators

In this paper a neural network heuristic dynamic programing (HDP) is use...
05/13/2022

Robustness of Control Design via Bayesian Learning

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

Code Repositories

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