Prediction of neural network performance by phenotypic modeling

by   Alexander Hagg, et al.

Surrogate models are used to reduce the burden of expensive-to-evaluate objective functions in optimization. By creating models which map genomes to objective values, these models can estimate the performance of unknown inputs, and so be used in place of expensive objective functions. Evolutionary techniques such as genetic programming or neuroevolution commonly alter the structure of the genome itself. A lack of consistency in the genotype is a fatal blow to data-driven modeling techniques: interpolation between points is impossible without a common input space. However, while the dimensionality of genotypes may differ across individuals, in many domains, such as controllers or classifiers, the dimensionality of the input and output remains constant. In this work we leverage this insight to embed differing neural networks into the same input space. To judge the difference between the behavior of two neural networks, we give them both the same input sequence, and examine the difference in output. This difference, the phenotypic distance, can then be used to situate these networks into a common input space, allowing us to produce surrogate models which can predict the performance of neural networks regardless of topology. In a robotic navigation task, we show that models trained using this phenotypic embedding perform as well or better as those trained on the weight values of a fixed topology neural network. We establish such phenotypic surrogate models as a promising and flexible approach which enables surrogate modeling even for representations that undergo structural changes.


page 1

page 2

page 3

page 4

page 5

page 6

page 7


Application of probabilistic modeling and automated machine learning framework for high-dimensional stress field

Modern computational methods, involving highly sophisticated mathematica...

Surrogate-Assisted Evolutionary Generative Design Of Breakwaters Using Deep Convolutional Networks

In the paper, a multi-objective evolutionary surrogate-assisted approach...

End-to-End Reinforcement Learning of Koopman Models for Economic Nonlinear MPC

(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic...

Gaussian process surrogate models for neural networks

The lack of insight into deep learning systems hinders their systematic ...

Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling

Recently, artificial neural networks have been gaining momentum in the f...

Parameter Tuning Strategies for Metaheuristic Methods Applied to Discrete Optimization of Structural Design

This paper presents several strategies to tune the parameters of metaheu...

Deep Model Intellectual Property Protection via Deep Watermarking

Despite the tremendous success, deep neural networks are exposed to seri...

Please sign up or login with your details

Forgot password? Click here to reset