Towards a Linear-Data Monotone Wrapper Algorithm For Machine Learning Algorithms

<br/>Machine learning algorithms (learners) are typically expected to produce monotone learning curves, meaning that their performance improves as the size of the training dataset increases. However, it is important to note that this behavior is not universally observed. Recently monotonicity of learning curves has gained renewed attention, as...

In Search of Best Learning Curve Model

Learning curves have been used extensively to analyse learners' behaviour and practical tasks such as model selection, speeding up training and tuning models. Nonetheless, we still have a relatively limited understanding of the behaviour of learning curves themselves, in particular, whether there exists a parametric function that can best model...

Different approaches to fitting and extrapolating the learning curve

Extrapolation of the learning curve provides an estimation of how much data is needed to achieve the desired performance. It can be beneficial when gathering data is complex, or computation resource is limited. One of the essential processes of learning curve extrapolation is curve fitting. This research first analyses the behaviour of existing...

To Tune or not to Tune: Hyperparameter Influence on the Learning Curve

A learning curve displays the measure of accuracy/error on test data of a machine learning algorithm trained on different amounts of training data. They can be modeled by parametric curve models that help predict accuracy improvement through curve extrapolation methods. However, these learning curves have only been mainly generated from default...

Explain Strange Learning Curves in Machine Learning

The learning curve illustrates how the generalization performance of the learner evolves with more training data. It can predict the amount of data needed for decent accuracy and the highest achievable accuracy. However, the behavior of learning curves is not well understood. Many assume that the more training data provided, the better the...

Factors related to dataset that influence the shape of learning curves

Although there are many promising applications of a learning curve in machine learning, such as model selection, we still know very little about what factors influence their behaviours. The aim is to study the impact of the inherent characteristics of the datasets on the learning shapes, which are noise, discretized input and dimensionality. We...

Are CNNs that Learn to Predict Image Statistics Invariant to Domain Shifts?

Yes, convolutional neural networks are domain-invariant, albeit to some limited extent. We explored the performance impact of domain shift for convolutional neural networks. We did this by designing new synthetic tasks, for which the network’s task was to map images to their mean, median, standard deviation, and variance pixel intensities. We...

Is the batch size affecting the performance of Regression CNNs ?

With an expectation of 8.3 trillion photos stored in 2021 [1], convolutional neural networks (CNN) are beginning to be preeminent in the field of image recognition. However, with this deep neural network (DNN) still being seen as a black box, it is hard to fully employ its capabilities. A need to tune hyperparameters is required to have a robust...

How does imbalanced data affect performance of regression CNNs?

This research provides an overview on how training Convolutional Neural Networks (CNNs) on imbalanced datasets affect the performance of the CNNs. Datasets could be imbalanced as a result of several reasons. There are for example naturally less samples of rare diseases. Since the network is trained less on those instances, this might lead to...

Go Deep or Go Home?

Does a convolutional neural network (CNN) always have to be deep to learn a task? This is an important question as deeper networks are generally harder to train. We trained shallow and deep CNNs and evaluated their performance on simple regression tasks, such as computing the mean pixel value of an image. For these simple tasks we show that...

Comparison of Linguistic Language Classification based on Origin and Data Driven Language Classification using the IPA and Clustering

Language similarity is very useful for enrichment data in both Natural Lanuguage Processing (NLP) and Automatic Speech Recognition (ASR). A clustering algorithm could provide an efficient means to define language similarity in a data-driven way. This research investigates the relation between linguistic classification by origin and data driven...

It sounds like Greek to me: Performance of phonetic representations for language identification

This paper compares the performance of two phonetic notations, IPA and ASJPcode, with the alphabetical notation for word-level language identification. Two machine learning models, a Multilayer Percerptron and a Logistic Regression model, are used to classify words using each of the three notations. With both models the IPA notation outperforms...

Detecting Rhyming Words

Rhyming words are one of the most important features in poems. They add rhythm to a poem, and poets use this literary device to portray emotion and meaning to their readers. Thus, detecting rhyming words will aid in adding emotions and enhancing readability when generating poems. Previous studies have been done on the topic of poem generation....

Extracting location context from transcripts: a comparison of ELMo and TF-IDF

Using transcripts of the TV-series FRIENDS, this paper explores the problem of predicting the location in which a sentence was said. The research focuses on using feature extraction on the sentences, and training a logistic regression model on those features. Specifically looking at the differences in performance between using ELMo and TF-IDF...

Using Skip-Gram Model to Predict from which Show a Given Line is

Text classification has a wide range of usage such as extracting the sentiment out of a product review, analyzing the topic of a document and spam detection. In this research, the text classification task is to predict from which TV-show a given line is. The skip-gram model, originally used to train the Word2Vec sentence embeddings [Mikolov et...

Gender bias in word embeddings of different languages

Word embeddings are useful for various applications, such as sentiment classification (Tang et al., 2014), word translation (Xing, Wang, Liu, &amp; Lin, 2015) and résumé parsing (Nasser, Sreejith, &amp; Irshad, 2018). Previous research has determined that word embeddings contain gender bias, which can be problematic in certain applications such...