Browse Articles

Identifying Neural Networks that Implement a Simple Spatial Concept

Zirvi et al. | Sep 13, 2022

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...

Evaluation of Microplastics in Japanese Fish Using Visual and Chemical Dissections

Srebnik et al. | Jan 20, 2021

Evaluation of Microplastics in Japanese Fish Using Visual and Chemical Dissections

Does the overuse of plastic in Japan poses an ecological risk to marine species and their consumers? Using visual and chemical dissection, all fish in this study were found to have microplastics present in their gastrointestinal tract, including two species that are typically eaten whole in Japan. Overall, these results are concerning as previous studies have found that microplastics can carry persistent organic pollutants. It is presumed that the increasing consumption of microplastics will have negative implications on organ systems such as the liver, gut, and hormones.

Read More...

Transfer Learning for Small and Different Datasets: Fine-Tuning A Pre-Trained Model Affects Performance

Gupta et al. | Oct 18, 2020

Transfer Learning for Small and Different Datasets: Fine-Tuning A Pre-Trained Model Affects Performance

In this study, the authors seek to improve a machine learning algorithm used for image classification: identifying male and female images. In addition to fine-tuning the classification model, they investigate how accuracy is affected by their changes (an important task when developing and updating algorithms). To determine accuracy, a set of images is used to train the model and then a separate set of images is used for validation. They found that the validation accuracy was close to the training accuracy. This study contributes to the expanding areas of machine learning and its applications to image identification.

Read More...

The effect of activation function choice on the performance of convolutional neural networks

Wang et al. | Sep 15, 2023

The effect of activation function choice on the performance of convolutional neural networks
Image credit: Tara Winstead

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...

The determinants and incentives of corporate greenhouse gas emission reduction

Liu et al. | Jun 04, 2021

The determinants and incentives of corporate greenhouse gas emission reduction

This study used hand-collected Greenhouse gas (GHG) emissions data from the Environmental Protection Agency (EPA) and aimed to understand the determinants and incentives of GHG emissions reduction. It explored how companies’ financials, Chief Executive Officer (CEO) compensation, and corporate governance affected GHG emissions. Results showed that companies reporting GHG emissions were wide-spread among the 48 industries represented by two-digit Standard Industrial Classification (SIC) codes.

Read More...

Propagation of representation bias in machine learning

Dass-Vattam et al. | Jun 10, 2021

Propagation of representation bias in machine learning

Using facial recognition as a use-case scenario, we attempt to identify sources of bias in a model developed using transfer learning. To achieve this task, we developed a model based on a pre-trained facial recognition model, and scrutinized the accuracy of the model’s image classification against factors such as age, gender, and race to observe whether or not the model performed better on some demographic groups than others. By identifying the bias and finding potential sources of bias, his work contributes a unique technical perspective from the view of a small scale developer to emerging discussions of accountability and transparency in AI.

Read More...

Search Articles

Search articles by title, author name, or tags

Clear all filters

Popular Tags

Browse by school level