Growing Machines Capable of Rapid Learning in Unknown Environments

Introduction

Despite major advances in the field of artificial intelligence, especially in the field of neural networks, these systems still pale in comparison to even simple biological intelligence. Current machine learning systems take many trials to learn, lack common sense, and often fail even if the environment only changes slightly.

Current Limitations

The enormous potential of autonomous machines remains unfulfilled, and we still lack robots to fill our dishwashers or go on autonomous search-and-rescue missions. The grand goal of GROW-AI is to create machines with a more general intelligence, allowing rapid adaptation in unknown situations.

Biological Inspiration

In stark contrast to current neural networks, whose architectures are designed by human experts and whose large number of parameters are optimized directly, evolution does not operate directly on the parameters of biological nervous systems. Instead, these nervous systems are grown and self-organize through a much smaller genetic program that produces rich behavioral capabilities right from birth and the ability to rapidly learn.

The Genomic Bottleneck

Neuroscience suggests this "genomic bottleneck" is an important regularizing constraint, allowing animals to generalize to new situations. However, currently, there does not exist a solution to creating a similar system artificially.

Proposed Solutions

We address this challenge with two ambitious ideas:

1. We will learn genomic bottleneck algorithms instead of manually designing them, exploiting recent advances in memory-augmented deep neural networks that can learn complex algorithms.
2. We will co-optimize task generators that provide the agents with the most effective learning environments.

Research Approach

Taking inspiration from the fields of artificial life, neurobiology, and machine learning, we will investigate if algorithmic growth is needed to understand and create intelligence.

Expected Outcomes

If successful, this project will greatly improve the autonomy of machines and significantly increase the range of real-world tasks they can solve.