EDEN: Evolutionary deep networks for efficient machine learning

Dufourq, Emmanuel; Bassett, Bruce A.

doi:10.1109/robomech.2017.8261132

Cited by 70 publications

(39 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, some authors have made used of neural architecture search for automatically optimizing the hyperparameters of CNN classifiers. For example, Dufourq and Bassett [80] presented EDEN, where they applied neuroevolution obtaining an accuracy of 88.3% in EMNIST Balanced and 99.3% in EMNIST Digits. More recently, [64] have used committees of neuroevolved CNNs using topology transfer learning, obtaining an accuracy of 95.35% in EMNIST Letters and 99.77% in EMNIST Digits.…”

Section: State Of the Artmentioning

confidence: 99%

A Survey of Handwritten Character Recognition with MNIST and EMNIST

2019

View full text Add to dashboard Cite

This paper summarizes the top state-of-the-art contributions reported on the MNIST dataset for handwritten digit recognition. This dataset has been extensively used to validate novel techniques in computer vision, and in recent years, many authors have explored the performance of convolutional neural networks (CNNs) and other deep learning techniques over this dataset. To the best of our knowledge, this paper is the first exhaustive and updated review of this dataset; there are some online rankings, but they are outdated, and most published papers survey only closely related works, omitting most of the literature. This paper makes a distinction between those works using some kind of data augmentation and works using the original dataset out-of-the-box. Also, works using CNNs are reported separately; as they are becoming the state-of-the-art approach for solving this problem. Nowadays, a significant amount of works have attained a test error rate smaller than 1% on this dataset; which is becoming non-challenging. By mid-2017, a new dataset was introduced: EMNIST, which involves both digits and letters, with a larger amount of data acquired from a database different than MNIST's. In this paper, EMNIST is explained and some results are surveyed.

show abstract

Section: State Of the Artmentioning

confidence: 99%

A Survey of Handwritten Character Recognition with MNIST and EMNIST

2019

View full text Add to dashboard Cite

show abstract

“…Multiple works [7,8,9,10,11] have used CNN models on MNIST dataset and have achieved results in excess of 99% accuracy. Apart from digit recognition, several attempts [12,13] have been made in handwritten character recognition with EMNIST datasets [12]. A bidirectional neural network is introduced in [14] which is capable of performing both image classification and image reconstruction by adding a style memory to the output layer of the network.…”

Section: Related Workmentioning

confidence: 99%

“…With full train set With 200 samp/class Cohen et al [12] 95.90% -Dufourq et al [13] 99.3% -TextCaps 99.79 ± 0.11% 98.96 ± 0.22%…”

Section: Emnist-digits Implementationmentioning

confidence: 99%

See 1 more Smart Citation

TextCaps: Handwritten Character Recognition With Very Small Datasets

Jayasundara

Jayasekara

et al. 2019

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Many localized languages struggle to reap the benefits of recent advancements in character recognition systems due to the lack of substantial amount of labeled training data. This is due to the difficulty in generating large amounts of labeled data for such languages and inability of deep learning techniques to properly learn from small number of training samples. We solve this problem by introducing a technique of generating new training samples from the existing samples, with realistic augmentations which reflect actual variations that are present in human hand writing, by adding random controlled noise to their corresponding instantiation parameters. Our results with a mere 200 training samples per class surpass existing character recognition results in the EMNIST-letter dataset while achieving the existing results in the three datasets: EMNIST-balanced, EMNIST-digits, and MNIST. We also develop a strategy to effectively use a combination of loss functions to improve reconstructions. Our system is useful in character recognition for localized languages that lack much labeled training data and even in other related more general contexts such as object recognition.

show abstract

“…All neural network architecture results with several ConvNets models configuring hyperparameters and applying regularization are shown in below Table I. By comparing the results of best models published in the literatures [19], [4] and [1]. In literature [19], SVC (Support Vector Classifier) is applied.…”

Section: Fig 6 Two Images From Two Classes Of Fashion-mnist Datasetmentioning

confidence: 99%

Hyperparameter Optimization and Regularization on Fashion-MNIST Classification

Greeshma¹,

Sreekumar²

2019

IJRTE

View full text Add to dashboard Cite

Nowadays the most exciting technology breakthrough has been the rise of the deep learning. In computer vision Convolutional Neural Networks (CNN or ConvNet) are the default deep learning model used for image classification problems. In these deep network models, feature extraction is figure out by itself and these models tend to perform well with huge amount of samples. Herein we explore the impact of various Hyper-Parameter Optimization (HPO) methods and regularization techniques with deep neural networks on FashionMNIST (F-MNIST) dataset which is proposed by Zalando Research. We have proposed deep ConvNet architectures with Data Augmentation and explore the impact of this by configuring the hyperparameters and regularization methods. As deep learning requires a lots of data, the insufficiency of image samples can be expand through various data augmentation methods like Cropping, Rotation, Flipping, and Shifting. The experimental results show impressive results on this new benchmarking dataset F-MNIST

show abstract

EDEN: Evolutionary deep networks for efficient machine learning

Cited by 70 publications

References 24 publications

A Survey of Handwritten Character Recognition with MNIST and EMNIST

A Survey of Handwritten Character Recognition with MNIST and EMNIST

TextCaps: Handwritten Character Recognition With Very Small Datasets

Hyperparameter Optimization and Regularization on Fashion-MNIST Classification

Contact Info

Product

Resources

About