Literature on Neural Architecture Search

@article{Li2017_nng,

title = {Hyperband - A Novel Bandit-Based Approach to Hyperparameter Optimization},

author = {Lisha Li and Kevin G Jamieson and Giulia DeSalvo and Afshin Rostamizadeh and Ameet Talwalkar},

url = {https://arxiv.org/abs/1603.06560},

year  = {2017},

date = {2017-01-01},

volume = {18},

pages = {185:1-185:52},

key = {journals/jmlr/LiJDRT17},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Stanley2009_mid,

title = {A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks},

author = {Kenneth O Stanley and David B D'Ambrosio and Jason Gauci},

url = {https://ieeexplore.ieee.org/document/6792316/},

doi = {10.1162/ARTL.2009.15.2.15202},

year  = {2009},

date = {2009-01-01},

volume = {15},

number = {2},

pages = {185-212},

key = {journals/alife/StanleyDG09},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Floreano2008_wpi,

title = {Neuroevolution - from architectures to learning},

author = {Dario Floreano and Peter Dürr and Claudio Mattiussi},

url = {https://link.springer.com/article/10.1007/s12065-007-0002-4},

doi = {10.1007/S12065-007-0002-4},

year  = {2008},

date = {2008-01-01},

volume = {1},

number = {1},

pages = {47-62},

key = {journals/evi/FloreanoDM08},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Roy2004_app,

title = {Designing Polymer Blends Using Neural Networks, Genetic Algorithms, and Markov Chains},

author = {N K Roy and Walter D Potter and D P Landau},

url = {https://dl.acm.org/citation.cfm?id=94034},

doi = {10.1023/B:APIN.0000021414.50728.34},

year  = {2004},

date = {2004-01-01},

volume = {20},

number = {3},

pages = {215-229},

key = {journals/apin/RoyPL04},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Angeline1994_qts,

title = {An evolutionary algorithm that constructs recurrent neural networks},

author = {Peter J Angeline and Gregory M Saunders and Jordan B Pollack},

url = {https://ieeexplore.ieee.org/document/265960/},

doi = {10.1109/72.265960},

year  = {1994},

date = {1994-01-01},

volume = {5},

number = {1},

pages = {54-65},

key = {journals/tnn/AngelineSP94},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kitano1990_uli,

title = {Designing Neural Networks Using Genetic Algorithms with Graph Generation System},

author = {Hiroaki Kitano},

url = {http://www.complex-systems.com/abstracts/v04_i04_a06/},

year  = {1990},

date = {1990-01-01},

volume = {4},

number = {4},

key = {journals/compsys/Kitano90},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1142/S1793351X22500027,

title = {Evolving Deep Neural Networks with Cultural Algorithms for Real-Time Industrial Applications},

author = {Faisal Waris and Robert G. Reynolds and Joonho Lee},

url = {https://doi.org/10.1142/S1793351X22500027},

doi = {10.1142/S1793351X22500027},

year  = {0000},

date = {0000-01-01},

urldate = {0000-01-01},

journal = {International Journal of Semantic Computing},

volume = {0},

number = {0},

pages = {1-32},

abstract = {The goal of this paper is to investigate the applicability of evolutionary algorithms to the design of real-time industrial controllers. Present-day “deep learning” (DL) is firmly established as a useful tool for addressing many practical problems. This has spurred the development of neural architecture search (NAS) methods in order to automate the model search activity. CATNeuro is a NAS algorithm based on the graph evolution concept devised by Neuroevolution of Augmenting Topologies (NEAT) but propelled by cultural algorithm (CA) as the evolutionary driver. The CA is a network-based, stochastic optimization framework inspired by problem solving in human cultures. Knowledge distribution (KD) across the network of graph models is a key to problem solving success in CAT systems. Two alternative mechanisms for KD across the network are employed. One supports cooperation (CATNeuro) in the network and the other competition (WM). To test the viability of each configuration prior to use in the industrial setting, they were applied to the design of a real-time controller for a two-dimensional fighting game. While both were able to beat the AI program that came with the fighting game, the cooperative method performed statistically better. As a result, it was used to track the motion of a trailer (in lateral and vertical directions) using a camera mounted on the tractor vehicle towing the trailer. In this second real-time application (trailer motion), the CATNeuro configuration was compared to the original NEAT (elitist) method of evolution. CATNeuro is found to perform statistically better than NEAT in many aspects of the design including model training loss, model parameter size, and overall model structure consistency. In both scenarios, the performance improvements were attributed to the increased model diversity due to the interaction of CA knowledge sources both cooperatively and competitively.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1177/01423312221119648,

title = {Optimal architecture artificial neural network model design with exploitative alpha gray wolf optimization for soft calibration of CO concentration measurements in electronic nose applications},

author = {Ozlem Imik Simsek and Baris Baykant Alagoz},

url = {https://doi.org/10.1177/01423312221119648},

doi = {10.1177/01423312221119648},

year  = {0000},

date = {0000-01-01},

urldate = {0000-01-01},

journal = {Transactions of the Institute of Measurement and Control},

volume = {0},

number = {0},

pages = {01423312221119648},

abstract = {The low-cost and small size solid-state sensor arrays are suitable to implement a wide-area electronic nose (e-nose) for real-time air quality monitoring. However, accuracy of these low-cost sensors is not adequate for precise measurements of pollutant concentrations. Artificial neural network (ANN) estimation models are used for the soft calibration of low-cost sensor array measurements and significantly improve the accuracy of low-cost multi-sensor measurements. However, optimality of neural architecture affects the performance of ANN estimation models, and optimization of the ANN architecture for a training data set is essential to improve data-driven modeling performance of ANNs to reach optimal neural complexity and improved generalization. In this study, an optimal architecture ANN estimator design scheme is suggested to improve the estimation performance of ANN models for e-nose applications. To this end, a gray wolf optimization (GWO) algorithm is modified, and an exploitative alpha gray wolf optimization (EA-GWO) algorithm is suggested. This modification enhances local exploitation skill of the best alpha gray wolf search agent, and thus allows the fine-tuning of ANN architectures by minimizing a multi-objective cost function that implements mean error search policy. Experimental study demonstrates the effectiveness of optimal architecture ANN models to estimate CO concentration from the low-cost multi-sensor data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{https://doi.org/10.1111/exsy.12690,

title = {Hybrid evolutionary network architecture search (HyENAS) for convolution class of deep neural networks with applications},

author = {Soniya and Lotika Singh and Sandeep Paul},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/exsy.12690},

doi = {https://doi.org/10.1111/exsy.12690},

journal = {Expert Systems},

volume = {n/a},

number = {n/a},

pages = {e12690},

abstract = {Abstract Convolutional Neural Networks (CNNs) and its variants are increasingly used across wide domain of applications achieving high performance measures. For high performance, application specific CNN architecture is required, hence the need for network architecture search (NAS) becomes essential. This paper proposes a hybrid evolutionary approach for network architecture search (HyENAS), and targets convolution class of neural networks. One of the significant contribution of this technique is to completely evolve the high performance network by simultaneously finding network structures and their corresponding parameters. An elegant string representation has been proposed which efficiently represents the network. The concept of sparse block evolving requisite layer wise features for dense network is deployed. This permits the network to dynamically evolve for a specific application. In comparison to the other state-of-art methods, the high performance of the proposed HyENAS approach is demonstrated across various benchmark data sets belonging to the domain of malariology, oncology, neurology, ophthalmology, and genomics. Further, to deploy the proposed model on lower hardware specification devices, another salient feature of the HyENAS technique is to seamlessly sift out the simpler network architecture with comparable accuracy.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{https://doi.org/10.1049/cvi2.12036,

title = {Control the number of skip-connects to improve robustness of the NAS algorithm},

author = {Bao Feng Zhang and Guo Qiang Zhou},

url = {https://ietresearch.onlinelibrary.wiley.com/doi/abs/10.1049/cvi2.12036},

doi = {https://doi.org/10.1049/cvi2.12036},

journal = {IET Computer Vision},

volume = {n/a},

number = {n/a},

abstract = {Abstract Recently, the gradient-based neural architecture search has made remarkable progress with the characteristics of high efficiency and fast convergence. However, two common problems in the gradient-based NAS algorithms are found. First, with the increase in the raining time, the NAS algorithm tends to skip-connect operation, leading to performance degradation and instability results. Second, another problem is no reasonable allocation of computing resources on valuable candidate network models. The above two points lead to the difficulty in searching the optimal sub-network and poor stability. To address them, the trick of pre-training the super-net is applied, so that each operation has an equal opportunity to develop its strength, which provides a fair competition condition for the convergence of the architecture parameters. In addition, a skip-controller is proposed to ensure each sampled sub-network with an appropriate number of skip-connects. The experiments were performed on three mainstream datasets CIFAR-10, CIFAR-100 and ImageNet, in which the improved method achieves comparable results with higher accuracy and stronger robustness.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}