The authors develop a new method for training machine learning algorithms to differentiate between hate speech and cultural speech in online platforms.
Read More...Battling cultural bias within hate speech detection: An experimental correlation analysis
The authors develop a new method for training machine learning algorithms to differentiate between hate speech and cultural speech in online platforms.
Read More...Comparison of spectral subtraction noise reduction algorithms
Here, the authors investigated methods to reduce noise in audio composed of real-word sounds. They specifically used two spectral subtraction noise reduction algorithms: stationary and non-stationary finding notable differences in noise improvements depending on the noise sources.
Read More...The Role of Race in the Stereotyping of a Speaker’s Accent as Native or Non-native
In the modern world, communication and mobility are no longer obstacles. A natural consequence is that people from all over the world are mixing like never before and national identity can no longer be determined simply by a person's appearance or manner of speech. In this article, the authors study how a person's accent interferes with the perception of a their national identity and proposes ways to eliminate such biases.
Read More...Identifying Neural Networks that Implement a Simple Spatial Concept
Modern artificial neural networks have been remarkably successful in various applications, from speech recognition to computer vision. However, it remains less clear whether they can implement abstract concepts, which are essential to generalization and understanding. To address this problem, the authors investigated the above vs. below task, a simple concept-based task that honeybees can solve, using a conventional neural network. They found that networks achieved 100% test accuracy when a visual target was presented below a black bar, however only 50% test accuracy when a visual target was presented below a reference shape.
Read More...The effect of activation function choice on the performance of convolutional neural networks
With the advance of technology, artificial intelligence (AI) is now applied widely in society. In the study of AI, machine learning (ML) is a subfield in which a machine learns to be better at performing certain tasks through experience. This work focuses on the convolutional neural network (CNN), a framework of ML, applied to an image classification task. Specifically, we analyzed the performance of the CNN as the type of neural activation function changes.
Read More...Search articles by title, author name, or tags