Analysis of k-Fold Cross-Validation over Hold-Out Validation on Colossal Datasets for Quality Classification

Yadav, Sanjay Kumar; Shukla, Sanyam

doi:10.1109/iacc.2016.25

Cited by 485 publications

(247 citation statements)

References 14 publications

Supporting

Mentioning

237

Contrasting

Unclassified

Order By: Relevance

“…In [20] a comparative study has been made between k-Fold cross-validation over hold-out validation on colossal datasets for quality classification. The results found show that for large datasets both methods give very close results.…”

Section: Experiments By Using the Holdout Methods For The Validationmentioning

confidence: 99%

Towards an optimal set of initial weights for a Deep Neural Network architecture

Saadi¹,

Belhadef²

2019

NNW

View full text Add to dashboard Cite

Modern neural network architectures are powerful models. They have been proven efficient in many fields, such as imaging and acoustic. However, these neural networks involve a long-running and time-consuming process. To accelerate the training process, we propose a two-stage approach based on data analysis and focus on the gravity center concept. The neural network is first trained on reduced data represented by a set of centroids of the original data points, and then the learned weights are used to initialize a second training phase of the neural network over the full-blown data. The design of deep neural networks is extremely difficult, and the primary objective is to achieve high performance. In this study, we apply the Taguchi method to select good values for the factors required to build the proposed architecture.

show abstract

Section: Experiments By Using the Holdout Methods For The Validationmentioning

confidence: 99%

Towards an optimal set of initial weights for a Deep Neural Network architecture

Saadi¹,

Belhadef²

2019

NNW

View full text Add to dashboard Cite

show abstract

“…They compared different feature extraction determination which algorithm is best suited in terms of execution time for Sentiment Analysis based on the given dataset [13]. K-fold cross-validation was studied in [14]. Since we had limited amounts of data, we use k-Fold cross-validation so to achieve unbiased prediction of the model we perform k-fold cross validation.…”

Section: Literature Reviewmentioning

confidence: 99%

Sentiment Analysis on New Currency in Kenya using Twitter Dataset

Noor

Turan

2020

IJID

View full text Add to dashboard Cite

Social media sites recently became popular, it is clear that it has major influence in society. Twitter is one of these sites, full of people’s opinions, where one can truck sentiment express about different kinds of topics. Sentiment analysis is one of the major interesting research areas nowadays. In this paper, we focused on Sentimental insight into the 2019 Kenya currency replacement. Kenyans citizens expressed their reaction over new banknotes. We perform sentiment analysis of the tweets from twitter using the Multinomial Naïve Bayes algorithm. We split our dataset using k-folder cross validation since we had limited amounts of data, so to achieve unbiased prediction of the model we obtained an average accuracy of 75.3%.

show abstract

“…This means our model could overfit to populations that appear more frequently. To reduce the chance of overfitting from population bias in the training set we could perform k-fold cross validation (Yadav & Shukla 2016) when splitting the sample set. K-fold validation splits the sample set into an arbitrary 'k' number of folds where one fold becomes the test set whilst the remaining folds are merged to form the training set.…”

Section: Limitations Of Our Modelmentioning

confidence: 99%

Deep-CEE I: fishing for galaxy clusters with deep neural nets

Chan

Stott

2019

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

We introduce Deep-CEE (Deep Learning for Galaxy Cluster Extraction and Evaluation), a proof of concept for a novel deep learning technique, applied directly to wide-field colour imaging to search for galaxy clusters, without the need for photometric catalogues. This technique is complementary to traditional methods and could also be used in combination with them to confirm galaxy cluster candidates. We use a state-of-the-art probabilistic algorithm, adapted to localise and classify galaxy clusters from other astronomical objects in SDSS imaging. As there is an abundance of labelled data for galaxy clusters from previous classifications in publicly available catalogues, we do not need to rely on simulated data. This means we keep our training data as realistic as possible, which is advantageous when training a deep learning algorithm. Ultimately, we will apply our model to surveys such as LSST and Euclid to probe wider and deeper into unexplored regions of the Universe. This will produce large samples of both high redshift and low mass clusters, which can be utilised to constrain both environment-driven galaxy evolution and cosmology.

show abstract

Analysis of k-Fold Cross-Validation over Hold-Out Validation on Colossal Datasets for Quality Classification

Cited by 485 publications

References 14 publications

Towards an optimal set of initial weights for a Deep Neural Network architecture

Towards an optimal set of initial weights for a Deep Neural Network architecture

Sentiment Analysis on New Currency in Kenya using Twitter Dataset

Deep-CEE I: fishing for galaxy clusters with deep neural nets

Contact Info

Product

Resources

About