Naive Artificial Intelligence

TL;DR

This paper introduces a deep unsupervised learning model that demonstrates fluid intelligence by solving intelligence tests without prior training, highlighting potential for modeling human cognitive processes.

Contribution

It presents a novel deep unsupervised latent-prediction network capable of solving intelligence tests without prior training, illustrating fluid intelligence in AI.

Findings

Deep networks can solve intelligence tests without prior training.

The model demonstrates fluid intelligence capabilities.

Potential to model human fluid intelligence computationally.

Abstract

In the cognitive sciences, it is common to distinguish between crystal intelligence, the ability to utilize knowledge acquired through past learning or experience and fluid intelligence, the ability to solve novel problems without relying on prior knowledge. Using this cognitive distinction between the two types of intelligence, extensively-trained deep networks that can play chess or Go exhibit crystal but not fluid intelligence. In humans, fluid intelligence is typically studied and quantified using intelligence tests. Previous studies have shown that deep networks can solve some forms of intelligence tests, but only after extensive training. Here we present a computational model that solves intelligence tests without any prior training. This ability is based on continual inductive reasoning, and is implemented by deep unsupervised latent-prediction networks. Our work demonstrates the potential fluid intelligence of deep networks. Finally, we propose that the computational principles underlying our approach can be used to model fluid intelligence in the cognitive sciences.