Nothing makes sense in deep learning, except in the light of evolution

by   Artem Kaznatcheev, et al.

Deep Learning (DL) is a surprisingly successful branch of machine learning. The success of DL is usually explained by focusing analysis on a particular recent algorithm and its traits. Instead, we propose that an explanation of the success of DL must look at the population of all algorithms in the field and how they have evolved over time. We argue that cultural evolution is a useful framework to explain the success of DL. In analogy to biology, we use `development' to mean the process converting the pseudocode or text description of an algorithm into a fully trained model. This includes writing the programming code, compiling and running the program, and training the model. If all parts of the process don't align well then the resultant model will be useless (if the code runs at all!). This is a constraint. A core component of evolutionary developmental biology is the concept of deconstraints – these are modification to the developmental process that avoid complete failure by automatically accommodating changes in other components. We suggest that many important innovations in DL, from neural networks themselves to hyperparameter optimization and AutoGrad, can be seen as developmental deconstraints. These deconstraints can be very helpful to both the particular algorithm in how it handles challenges in implementation and the overall field of DL in how easy it is for new ideas to be generated. We highlight how our perspective can both advance DL and lead to new insights for evolutionary biology.


page 1

page 2

page 3

page 4


Evolved Open-Endedness in Cultural Evolution: A New Dimension in Open-Ended Evolution Research

The goal of Artificial Life research, as articulated by Chris Langton, i...

Twin Systems for DeepCBR: A Menagerie of Deep Learning and Case-Based Reasoning Pairings for Explanation and Data Augmentation

Recently, it has been proposed that fruitful synergies may exist between...

Explaining Deep Learning-Based Networked Systems

While deep learning (DL)-based networked systems have shown great potent...

DLSpec: A Deep Learning Task Exchange Specification

Deep Learning (DL) innovations are being introduced at a rapid pace. How...

Code Smells in Machine Learning Systems

As Deep learning (DL) systems continuously evolve and grow, assuring the...

SLDR-DL: A Framework for SLD-Resolution with Deep Learning

This paper introduces an SLD-resolution technique based on deep learning...

Please sign up or login with your details

Forgot password? Click here to reset