A Study of Fitness Landscapes for Neuroevolution
- URL: http://arxiv.org/abs/2001.11272v1
- Date: Thu, 30 Jan 2020 11:53:55 GMT
- Title: A Study of Fitness Landscapes for Neuroevolution
- Authors: Nuno M. Rodrigues, Sara Silva, Leonardo Vanneschi
- Abstract summary: We use fitness landscapes to study the dynamics of meta-heuristics.
We also use them to infer useful information about the predictive ability of the method.
The results show that these measures are appropriate for estimating both the optimization power and the generalization ability of the considered neuroevolution configurations.
- Score: 4.930887920982693
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Fitness landscapes are a useful concept to study the dynamics of
meta-heuristics. In the last two decades, they have been applied with success
to estimate the optimization power of several types of evolutionary algorithms,
including genetic algorithms and genetic programming. However, so far they have
never been used to study the performance of machine learning algorithms on
unseen data, and they have never been applied to neuroevolution. This paper
aims at filling both these gaps, applying for the first time fitness landscapes
to neuroevolution and using them to infer useful information about the
predictive ability of the method. More specifically, we use a grammar-based
approach to generate convolutional neural networks, and we study the dynamics
of three different mutations to evolve them. To characterize fitness
landscapes, we study autocorrelation and entropic measure of ruggedness. The
results show that these measures are appropriate for estimating both the
optimization power and the generalization ability of the considered
neuroevolution configurations.
Related papers
- Enhancing learning in artificial neural networks through cellular heterogeneity and neuromodulatory signaling [52.06722364186432]
We propose a biologically-informed framework for enhancing artificial neural networks (ANNs)
Our proposed dual-framework approach highlights the potential of spiking neural networks (SNNs) for emulating diverse spiking behaviors.
We outline how the proposed approach integrates brain-inspired compartmental models and task-driven SNNs, bioinspiration and complexity.
arXiv Detail & Related papers (2024-07-05T14:11:28Z) - Evolutionary Multi-objective Optimisation in Neurotrajectory Prediction [0.0]
This work makes a progressive step forward in neuroevolution for vehicle trajectory prediction.
To this end, rich ANNs composed of CNNs and Long-short Term Memory Network are adopted.
Two well-known and robust Multi-objective Evolutionary optimisation (EMO) algorithms, NSGA-II and MOEA/D are also adopted.
arXiv Detail & Related papers (2023-08-04T21:06:26Z) - Phylogeny-informed fitness estimation [58.720142291102135]
We propose phylogeny-informed fitness estimation, which exploits a population's phylogeny to estimate fitness evaluations.
Our results indicate that phylogeny-informed fitness estimation can mitigate the drawbacks of down-sampled lexicase.
This work serves as an initial step toward improving evolutionary algorithms by exploiting runtime phylogenetic analysis.
arXiv Detail & Related papers (2023-06-06T19:05:01Z) - Initial Steps Towards Tackling High-dimensional Surrogate Modeling for
Neuroevolution Using Kriging Partial Least Squares [0.0]
Surrogate-assisted evolutionary algorithms (SAEAs) aim to use efficient computational models with the goal of approximating the fitness function in evolutionary computation systems.
An emergent and exciting area that has received little attention from the SAEAs community is in neuroevolution.
We demonstrate how one can use a Kriging Partial Least Squares method that allows efficient computation of good approximate surrogate models.
arXiv Detail & Related papers (2023-05-05T15:17:03Z) - Neuroevolution of Physics-Informed Neural Nets: Benchmark Problems and
Comparative Results [25.12291688711645]
Physics-informed neural networks (PINNs) are one of the key techniques at the forefront of recent advances.
PINNs' unique loss formulations lead to a high degree of complexity and ruggedness that may not be conducive for gradient descent.
Neuroevolution algorithms, with their superior global search capacity, may be a better choice for PINNs.
arXiv Detail & Related papers (2022-12-15T05:54:16Z) - Neuroevolutionary Multi-objective approaches to Trajectory Prediction in
Autonomous Vehicles [2.9552300389898094]
We focus on the intersection of neuroevolution and evolutionary multi-objective optimization.
We study a rich convolutional neural network composed of a CNN and Long-short Term Memory network.
We show how these objectives have either a positive or detrimental effect in neuroevolution for trajectory prediction in autonomous vehicles.
arXiv Detail & Related papers (2022-05-04T15:03:26Z) - Applications of Gaussian Mutation for Self Adaptation in Evolutionary
Genetic Algorithms [0.0]
In 1960, the first genetic algorithm was developed by John H. Holland and his student.
We explore the mathematical intuition of the genetic algorithm in developing systems capable of evolving using Gaussian mutation.
arXiv Detail & Related papers (2022-01-02T04:18:25Z) - Self-Supervised Graph Representation Learning for Neuronal Morphologies [75.38832711445421]
We present GraphDINO, a data-driven approach to learn low-dimensional representations of 3D neuronal morphologies from unlabeled datasets.
We show, in two different species and across multiple brain areas, that this method yields morphological cell type clusterings on par with manual feature-based classification by experts.
Our method could potentially enable data-driven discovery of novel morphological features and cell types in large-scale datasets.
arXiv Detail & Related papers (2021-12-23T12:17:47Z) - Dynamic Neural Diversification: Path to Computationally Sustainable
Neural Networks [68.8204255655161]
Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks.
We explore the diversity of the neurons within the hidden layer during the learning process.
We analyze how the diversity of the neurons affects predictions of the model.
arXiv Detail & Related papers (2021-09-20T15:12:16Z) - Emergent Hand Morphology and Control from Optimizing Robust Grasps of
Diverse Objects [63.89096733478149]
We introduce a data-driven approach where effective hand designs naturally emerge for the purpose of grasping diverse objects.
We develop a novel Bayesian Optimization algorithm that efficiently co-designs the morphology and grasping skills jointly.
We demonstrate the effectiveness of our approach in discovering robust and cost-efficient hand morphologies for grasping novel objects.
arXiv Detail & Related papers (2020-12-22T17:52:29Z) - The Neural Coding Framework for Learning Generative Models [91.0357317238509]
We propose a novel neural generative model inspired by the theory of predictive processing in the brain.
In a similar way, artificial neurons in our generative model predict what neighboring neurons will do, and adjust their parameters based on how well the predictions matched reality.
arXiv Detail & Related papers (2020-12-07T01:20:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.