ES-HyperNEAT
PulseAugur coverage of ES-HyperNEAT — every cluster mentioning ES-HyperNEAT across labs, papers, and developer communities, ranked by signal.
-
New method optimizes ES-HyperNEAT training, cutting costs by 41.6%
Researchers have developed a data-driven method for early stopping in hyperparameter configurations for ES-HyperNEAT, an evolutionary algorithm. This approach uses a binary classification on fitness trajectories to iden…
-
Spatially Partitioned Experts improve neuroevolution accuracy by 106%
Researchers have developed a novel approach to neuroevolution called Spatially Partitioned Experts (SPE) to address the central bias issue in Evolvable-Substrate HyperNEAT (ES-HyperNEAT). This bias causes ES-HyperNEAT t…
-
ES-HyperNEAT hyperparameter optimization shows transferability on MNIST
Researchers have investigated hyperparameter optimization for the ES-HyperNEAT algorithm using the Tree-structured Parzen Estimator (TPE) approach. Applied to the MNIST classification task, TPE successfully navigated ov…
-
ES-HyperNEAT hyperparameter optimization using TPE shows promise
A new study explores optimizing hyperparameters for ES-HyperNEAT, a neuroevolutionary algorithm, using the Tree-structured Parzen Estimator (TPE) approach. The research investigated over 3 billion hyperparameter combina…
-
New EMR-HyperNEAT method accelerates neuroevolution with tensorization
Researchers have developed EMR-HyperNEAT, a novel approach to neuroevolution that significantly accelerates the process of evolving large-scale neural network substrates. This new method overcomes limitations of previou…
-
New JAX implementation tackles ES-HyperNEAT scaling bottleneck
Researchers have developed JAX-ESHN, a new JAX-based implementation designed to parallelize ES-HyperNEAT on GPUs. This implementation addresses the quadtree bottleneck that previously limited scalability in coordinate-b…