DeepAI AI Chat
Log In Sign Up

Learning Division with Neural Arithmetic Logic Modules

by   Bhumika Mistry, et al.

To achieve systematic generalisation, it first makes sense to master simple tasks such as arithmetic. Of the four fundamental arithmetic operations (+,-,×,÷), division is considered the most difficult for both humans and computers. In this paper we show that robustly learning division in a systematic manner remains a challenge even at the simplest level of dividing two numbers. We propose two novel approaches for division which we call the Neural Reciprocal Unit (NRU) and the Neural Multiplicative Reciprocal Unit (NMRU), and present improvements for an existing division module, the Real Neural Power Unit (Real NPU). Experiments in learning division with input redundancy on 225 different training sets, find that our proposed modifications to the Real NPU obtains an average success of 85.3% improving over the original by 15.1%. In light of the suggestion above, our NMRU approach can further improve the success to 91.6%.


Neural Power Units

Conventional Neural Networks can approximate simple arithmetic operation...

A Primer for Neural Arithmetic Logic Modules

Neural Arithmetic Logic Modules have become a growing area of interest, ...

Quantum arithmetic operations based on quantum Fourier transform on signed integers

The quantum Fourier transform brings efficiency in many respects, especi...

High Speed SRT Divider for Intelligent Embedded System

Increasing development in embedded systems, VLSI and processor design ha...

Improving MATLAB's isprime performance without arbitrary-precision arithmetic

MATLAB is a numerical computing platform used by scientists, engineers, ...

Neural Arithmetic Logic Units

Neural networks can learn to represent and manipulate numerical informat...

Measuring Arithmetic Extrapolation Performance

The Neural Arithmetic Logic Unit (NALU) is a neural network layer that c...