Reinforcement learning (RL) is a form of machine learning that can be harnessed to develop artificial intelligence by exposing the intelligence to multiple generations of data. The study demonstrates how reply buffer reward mechanics can inform the creation of new pruning methods to improve RL efficiency.

The phenomenon of dying trees and plants in areas affected by acid rain has become increasingly problematic in recent times. Is there any method to efficiently utilize the rainwater and reduce the harmfulness of acid rain or make it beneficial to plants? This study aimed to investigate the potential of neutralizing acid rainwater infiltrating the soil to increase soil pH, produce beneficial salts for plants, and support better plant growth. To test this hypothesis, precipitation samples were collected from six states in the U.S. in 2022, and the pH of the acid rain was measured to obtain a representative pH value for the country. Experiments were then conducted to simulate the neutralization of acid rain and the subsequent change in soil pH levels. To evaluate the effectiveness and feasibility of this method, cat grass was planted in pots of soil soaked with solutions mimicking acid rain, with control and experimental groups receiving neutralizing agents (ammonium hydroxide) or not. Plant growth was measured by analyzing the height of the plants. Results demonstrated that neutralizing agents were effective in improving soil pH levels and that the resulting salts produced were beneficial to the growth of the grass. The findings suggest that this method could be applied on a larger agricultural scale to reduce the harmful effects of acid rain and increase agricultural efficiency.

Semantic segmentation - labelling each pixel in an image to a specific class- models require large amounts of manually labeled and collected data to train.

Neural machine translation (NMT) is a software that uses neural network techniques to translate text from one language to another. However, one of the most famous NMT models—Google Translate—failed to give an accurate English translation of a famous Korean nursery rhyme, "Airplane" (비행기). The authors fine-tuned a pre-trained model first with a dataset from the lyrics domain, and then with a smaller dataset containing the rhythmical properties, to teach the model to translate rhythmically accurate lyrics. This stacked fine-tuning method resulted in an NMT model that could maintain the rhythmical characteristics of lyrics during translation while single fine-tuned models failed to do so.

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.

The goal of this study was to determine the if carbohydrates or complex carbohydrates are better for athlete's performance in anaerobic and aerobic exercise. Ultimately, we found that, when one’s schedule only allows for 30 minutes to eat before a workout, the best pre-workout meal for optimal glycogen levels to prompt muscle hypertrophy, strength increases, and better endurance is one that is simple carbohydrate-heavy.

In this study, three models are used to test the hypothesis that data-centric artificial intelligence (AI) will improve the performance of machine learning.

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.

The burning of fossil fuels, leading to an increased amount of carbon emissions, is the main cause of acid rain. Acid rain affects the process of photosynthesis, which makes the topic valuable to investigate. Our group utilizes plants to further investigate the relationship between pH value and photosynthesis. In this experiment, our group hypothesized that rain with a lower pH will decrease the rate of photosynthesis, causing less oxygen to be produced in the reaction.

Wearing face masks has become a common occurrence in everyday life and during athletics due to the spread of diseases. This study tested if masks would affect blood percent saturation of hemoglobin (SpO₂) during treadmill exercise. The data analysis showed that mask type, time, and the interaction of mask type and time were significant results, regardless of physical ability. These results may assist athletes in understanding the differences between training and competing with and without a mask.