Number Sequence Prediction Problems and Computational Powers of Neural Network Models

05/19/2018
by   Hyoungwook Nam, et al.
0

Inspired by number series tests to measure human intelligence, we suggest number sequence prediction tasks to assess neural network models' computational powers for solving algorithmic problems. We define complexity and difficulty of a number sequence prediction task with the structure of the smallest automation that can generate the sequence. We suggest two types of number sequence prediction problems: the number-level and the digit-level problems. The number-level problems format sequences as 2-dimensional grids of digits, and the digit-level problem provides a single digit input per a time step, hence solving this problem is equivalent to modeling a sequential state automation. The complexity of a number-level sequence problem can be defined with the depth of an equivalent combinatorial logic. Experimental results with CNN models suggest that they are capable of learning the compound operations of the number-level sequence generation rules but the depths of the compound operations are limited. For the digit-level problems, GRU and LSTM models can solve the problems with complexity of finite state automations, but they cannot solve the problems with complexity of pushdown automations or Turing machines. The results show that our number sequence prediction problems effectively evaluate machine learning models' computational capabilities.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/13/2021

Neural Sequence-to-grid Module for Learning Symbolic Rules

Logical reasoning tasks over symbols, such as learning arithmetic operat...
research
03/22/2021

Extracting the Unknown from Long Math Problems

In problem solving, understanding the problem that one seeks to solve is...
research
07/13/2020

Predicting Sequences of Traversed Nodes in Graphs using Network Models with Multiple Higher Orders

We propose a novel sequence prediction method for sequential data captur...
research
06/17/2022

KitBit: A New AI Model for Solving Intelligence Tests and Numerical Series

The resolution of intelligence tests, in particular numerical sequences,...
research
04/18/2018

Deep Generative Networks For Sequence Prediction

This thesis investigates unsupervised time series representation learnin...
research
02/02/2021

Recurrent Neural Network for MoonBoard Climbing Route Classification and Generation

Classifying the difficulties of climbing routes and generating new route...
research
09/24/2020

Pebble-Depth

In this paper we introduce a new formulation of Bennett's logical depth ...

Please sign up or login with your details

Forgot password? Click here to reset