Evolutionary deep learning based on deep convolutional neural network for anime storyboard recognition

Fujino, Saya; Hatanaka, Taichi; Mori, Naoki; Matsumoto, Keinosuke

doi:10.1016/j.neucom.2018.05.124

Cited by 24 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, it becomes a self-supervised learning method. As the CRC score is not differential, to maximize it one may choose derivative-free algorithms, e.g., evolutionary methods [11][12][13][14] or particle filter optimization [15][16][17]. The biggest obstacle to implement the above idea may come from the computation, as such optimization methods are much more computationally expensive than gradient-based ones.…”

Section: Discussionmentioning

confidence: 99%

Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks

Liu¹

2021

Preprint

View full text Add to dashboard Cite

This paper is concerned with image classification based on deep convolutional neural networks (CNNs). The focus is centered around the following question: given a set of candidate CNN models, how to select the right one that has the best generalization property for the current task? Present model selection methods require access to a batch of labeled data for defining a performance metric, such as the cross-entropy loss, the classification error rate, the negative log-likelihood, and so on. In many practical cases, however, labeled data are not available in time as labeling itself is a time-consuming and expensive task. To this end, this paper presents an approach to CNN model selection using only unlabeled data. This method is developed based on a principle termed consistent relative confidence (CRC). The effectiveness and efficiency of the presented method are demonstrated by extensive experimental studies based on datasets MNIST and FasionM-NIST.

show abstract

Section: Discussionmentioning

confidence: 99%

Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks

Liu¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…a) The synergy between optimization and learning: Deep learning problems are in essence high-dimensional problems with the potential to contain millions or billions of decision variables. Although evolutionary algorithms have shown competitive results on high-dimensional learning problems [235,236], research on devising population-based algorithms to tackle large-scale learning problems is scarce [237][238][239][240][241][242]. Population-based metaheuristics in general, and evolutionary algorithms in particular, are suited for environments that require hard exploration.…”

Section: B Potential Areas For Future Researchmentioning

confidence: 99%

A Review of Population-Based Metaheuristics for Large-Scale Black-Box Global Optimization—Part II

Omidvar

Yao

2022

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

This paper is the second part of a two-part survey series on large-scale global optimization. The first part covered two major algorithmic approaches to large-scale optimization, namely decomposition methods and hybridization methods such as memetic algorithms and local search. In this part we focus on sampling and variation operators, approximation and surrogate modeling, initialization methods, and parallelization. We also cover a range of problem areas in relation to large-scale global optimization, such as multi-objective optimization, constraint handling, overlapping components, the component imbalance issue, and benchmarks, and applications. The paper also includes a discussion on pitfalls and challenges of current research and identifies several potential areas of future research.

show abstract

“…Data Types: Evolutionary DNN construction approaches have been applied to various data types, such as images [13], [59], [108], [109], speech [128], [133], [148], and texts [15], [110]. In particular, tremendous research effort has been devoted to solving the image classification problem.…”

Section: A Applicationsmentioning

confidence: 99%

A Survey on Evolutionary Construction of Deep Neural Networks

Xun

Qin

Gong

et al. 2021

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

Automated construction of deep neural networks (DNNs) has become a research hot spot nowadays because DNN's performance is heavily influenced by its architecture and parameters, which are highly task-dependent, but it is notoriously difficult to find the most appropriate DNN in terms of architecture and parameters to best solve a given task. In this work, we provide an insight into the automated DNN construction process by formulating it into a multilevel multiobjective large-scale optimization problem with constraints, where the nonconvex, nondifferentiable, and black-box nature of this problem make evolutionary algorithms (EAs) to stand out as a promising solver. Then, we give a systematical review of existing evolutionary DNN construction techniques from different aspects of this optimization problem and analyze the pros and cons of using EA-based methods in each aspect. This work aims to help DNN researchers to better understand why, where, and how to utilize EAs for automated DNN construction and meanwhile, help EA researchers to better understand the task of automated DNN construction so that they may focus more on EA-favored optimization scenarios to devise more effective techniques.

show abstract

Evolutionary deep learning based on deep convolutional neural network for anime storyboard recognition

Cited by 24 publications

References 9 publications

Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks

Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks

A Review of Population-Based Metaheuristics for Large-Scale Black-Box Global Optimization—Part II

A Survey on Evolutionary Construction of Deep Neural Networks

Contact Info

Product

Resources

About