Browse Articles

This study utilizes machine learning models to predict missing and unclear signs from the Indus script, a writing system from an ancient civilization in the Indian subcontinent.

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

Although commonly associated with cryptocurrency, blockchains offer security that other databases could benefit from. These student authors tested a blockchain database framework, and by tracking runtime of four independent variables, they prove this framework is feasible for application.

The authors designed a system that runs off of body heat to track body temperature that could help prevent injuries that result from elevated body temperature.

Here, seeking to better understand the control algorithms used in autonomous vehicles, the authors compared the Stanley and pure pursuit control algorithms along with a new version of each. Unexpectedly, they found that no control algorithm offered optimal performance, but rather resulted in tradeoffs between the various ideal results.

Here, beginning from an initial interest in the possibility to use a computer to automatically solve a geometry diagram parser, the authors developed their own Fast Geometry Diagram Parser (FastGDP) that uses clustering and corner information. They compared their own methods to a more widely available, method, GeoSolver, finding their own to be an order of magnitude faster in most cases that they considered.

In this study, the authors present proposed cryptographic controls for election sites with the hypothesis that this will mitigate risk and remediate vulnerabilities.

While remarkable in its ability to mirror human cognition, machine learning and its associated algorithms often require extensive data to prove effective in completing tasks. However, data is not always plentiful, with unpredictable events occurring throughout our daily lives that require flexibility by artificial intelligence utilized in technology such as personal assistants and self-driving vehicles. Driven by the need for AI to complete tasks without extensive training, the researchers in this article use fluid intelligence assessments to develop an algorithm capable of generalization and abstraction. By forgoing prioritization on skill-based training, this article demonstrates the potential of focusing on a more generalized cognitive ability for artificial intelligence, proving more flexible and thus human-like in solving unique tasks than skill-focused algorithms.