Search Results for author:
Found 16 papers, 1 papers with code
NeuroLGP-SM: Scalable Surrogate-Assisted Neuroevolution for Deep Neural Networks
This efficiency advantage adds to the overall appeal of our proposed NeuroLGP-SM in optimising the configuration of large DNNs.
NeuroLGP-SM: A Surrogate-assisted Neuroevolution Approach using Linear Genetic Programming
The amalgamation of these two techniques culminates in our proposed methodology known as the NeuroLGP-Surrogate Model (NeuroLGP-SM).
Evolutionary Multi-objective Optimisation in Neurotrajectory Prediction
Two well-known and robust Evolutionary Multi-objective Optimisation (EMO) algorithms, NSGA-II and MOEA/D are also adopted.
Initial Steps Towards Tackling High-dimensional Surrogate Modeling for Neuroevolution Using Kriging Partial Least Squares
This refers to the use of evolutionary algorithms in the automatic configuration of artificial neural network (ANN) architectures, hyper-parameters and/or the training of ANNs.
Evolving the MCTS Upper Confidence Bounds for Trees Using a Semantic-inspired Evolutionary Algorithm in the Game of Carcassonne
In this work, we use Evolutionary Algorithms (EAs) to evolve mathematical expressions with the goal to substitute the UCT formula and use the evolved expressions in MCTS.
Highlights of Semantics in Multi-objective Genetic Programming
Semantics is a growing area of research in Genetic programming (GP) and refers to the behavioural output of a Genetic Programming individual when executed.
ViT-BEVSeg: A Hierarchical Transformer Network for Monocular Birds-Eye-View Segmentation
In this paper, we evaluate the use of vision transformers (ViT) as a backbone architecture to generate BEV maps.
Neuroevolutionary Multi-objective approaches to Trajectory Prediction in Autonomous Vehicles
The incentive for using Evolutionary Algorithms (EAs) for the automated optimization and training of deep neural networks (DNNs), a process referred to as neuroevolution, has gained momentum in recent years.
On the Evolution of the MCTS Upper Confidence Bounds for Trees by Means of Evolutionary Algorithms in the Game of Carcassonne
Monte Carlo Tree Search (MCTS) is a sampling best-first method to search for optimal decisions.
Semantics in Multi-objective Genetic Programming
This is then used to compute a distance between the pivot and every individual in the population.
Semantic Neighborhood Ordering in Multi-objective Genetic Programming based on Decomposition
We show, for the first time, how we can promote semantic diversity in MOEA/D in Genetic Programming.
Neuroevolution in Deep Learning: The Role of Neutrality
A variety of methods have been applied to the architectural configuration and learning or training of artificial deep neural networks (DNN).
Promoting Semantics in Multi-objective Genetic Programming based on Decomposition
The study of semantics in Genetic Program (GP) deals with the behaviour of a program given a set of inputs and has been widely reported in helping to promote diversity in GP for a range of complex problems ultimately improving evolutionary search.
Semantic-based Distance Approaches in Multi-objective Genetic Programming
We empirically and consistently show how by naturally handling semantic distance as an additional criterion to be optimised in MOGP leads to better performance when compared to canonical methods and SSC.
Statistical Tree-based Population Seeding for Rolling Horizon EAs in General Video Game Playing
Furthermore, we tackle the former limitation by employing a mechanism that allows us to seed part of the population using Monte Carlo Tree Search, a method that has dominated multiple General Video Game AI competitions.
Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges
This paper presents a comprehensive survey, discussion and evaluation of the state-of-the-art works on using EAs for architectural configuration and training of DNNs.
