methodology-8

Evolutionary Algorithms

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in evolutionary-algorithms-17

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find evolutionary-algorithms-17 models and implementations

facebookresearch/LaMCTS

2 papers 443

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Progressive Neural Architecture Search

K. Murphy, Li-Jia Li, Li Fei-Fei, A. Yuille, Jonathon Shlens, Chenxi Liu, Barret Zoph, Jonathan Huang, Wei Hua•Fri Dec 01 2017

This work proposes a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms using a sequential model-based optimization (SMBO) strategy.

2105

Content

aadharna/UntouchableThunder

2 papers 16

0

Paper Graph

Evolution-Guided Policy Gradient in Reinforcement Learning

Shauharda Khadka, Kagan Tumer•Mon Apr 30 2018

Evolutionary Reinforcement Learning (ERL), a hybrid algorithm that leverages the population of an EA to provide diversified data to train an RL agent, and reinserts the RL agent into theEA population periodically to inject gradient information into the EA.

275 0

Paper Graph

Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

J. Clune, Kenneth O. Stanley, J. Lehman, Vashisht Madhavan, F. Such, Edoardo Conti•Sun Dec 17 2017

It is shown that combining DNNs with novelty search, which was designed to encourage exploration on tasks with deceptive or sparse reward functions, can solve a high-dimensional problem on which reward-maximizing algorithms fail, and expands the sense of the scale at which GAs can operate.

739 0

Paper Graph

Neural Architecture Optimization

Tao Qin, Fei Tian, Tie-Yan Liu, Renqian Luo•Tue Aug 21 2018

Experiments show that the architecture discovered by this simple and efficient method to automatic neural architecture design based on continuous optimization is very competitive for image classification task on CIFAR-10 and language modeling task on PTB, outperforming or on par with the best results of previous architecture search methods with a significantly reduction of computational resources.

697 0

Paper Graph

Tree Search vs Optimization Approaches for Map Generation

J. Togelius, A. Khalifa, Debosmita Bhaumik, M. Green•Tue Mar 26 2019

This work investigates the applicability of several tree search methods to level generation and compares them systematically with several optimization algorithms, including evolutionary algorithms, and introduces two new representations that can help tree search algorithms deal with the large branching factor of the generation problem.

4 0

Paper Graph

Regularized Evolution for Image Classifier Architecture Search

Esteban Real, Quoc V. Le, Yanping Huang, A. Aggarwal•Sun Feb 04 2018

This work evolves an image classifier---AmoebaNet-A---that surpasses hand-designs for the first time and gives evidence that evolution can obtain results faster with the same hardware, especially at the earlier stages of the search.

3233 0

Paper Graph

GenAttack: practical black-box attacks with gradient-free optimization

Supriyo Chakraborty, Yash Sharma, M. Alzantot, M. Srivastava•Sun May 27 2018

GenAttack is introduced, a gradient-free optimization technique that uses genetic algorithms for synthesizing adversarial examples in the black-box setting and can successfully attack some state-of-the-art ImageNet defenses, including ensemble adversarial training and non-differentiable or randomized input transformations.

281 0

Paper Graph

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

J. Clune, Anh Totti Nguyen, J. Yosinski•Wed Dec 03 2014

This work takes convolutional neural networks trained to perform well on either the ImageNet or MNIST datasets and finds images with evolutionary algorithms or gradient ascent that DNNs label with high confidence as belonging to each dataset class, and produces fooling images, which are then used to raise questions about the generality of DNN computer vision.

3410 0

Paper Graph

IOHanalyzer: Detailed Performance Analyses for Iterative Optimization Heuristics

Hongya Wang, Diederick Vermetten, Furong Ye, Carola Doerr, Thomas Bäck•Tue Jul 07 2020

Key advantages of IOHanalyzer over other performance analysis packages are its highly interactive design, which allows users to specify the performance measures, ranges, and granularity that are most useful for their experiments, and the possibility to analyze not only performance traces, but also the evolution of dynamic state parameters.

62 0

Paper Graph

Large-Scale Evolution of Image Classifiers

Esteban Real, Quoc V. Le, Jie Tan, Alexey Kurakin, Saurabh Saxena, Sherry Moore, Andrew Selle, Y. Suematsu•Thu Mar 02 2017

It is shown that it is now possible to evolve models with accuracies within the range of those published in the last year, starting from trivial initial conditions and reaching accuracies of 94.6% and 77.0%, respectively.

1726 0

Paper Graph

Adding a benchmark result helps the community track progress.