Search Results for author:
Found 9 papers, 2 papers with code
Asynchronous Evolution of Deep Neural Network Architectures
Next, it was evaluated in 11-bit multiplexer design (a single-population discovery task with extended variability), where a 14-fold speedup was observed.
Accelerating Evolution Through Gene Masking and Distributed Search
In building practical applications of evolutionary computation (EC), two optimizations are essential.
EVOTER: Evolution of Transparent Explainable Rule-sets
The approach is evaluated in several prediction/classification and prescription/policy search domains with and without a surrogate.
DIAS: A Domain-Independent Alife-Based Problem-Solving System
A domain-independent problem-solving system based on principles of Artificial Life is introduced.
Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription
Using this data, it is possible to learn a surrogate model, and with that model, evolve a decision strategy that optimizes the outcomes.
Regularized Evolutionary Population-Based Training
This paper presents an algorithm called Evolutionary Population-Based Training (EPBT) that interleaves the training of a DNN's weights with the metalearning of loss functions.
Enhanced Optimization with Composite Objectives and Novelty Pulsation
This paper improves this approach further by introducing novelty pulsation, i. e. a systematic method to alternate between novelty selection and local optimization.
Enhanced Optimization with Composite Objectives and Novelty Selection
An important benefit of multi-objective search is that it maintains a diverse population of candidates, which helps in deceptive problems in particular.
Evolving Deep Neural Networks
The success of deep learning depends on finding an architecture to fit the task.
