Gauging Biases in Various Deep Learning AI Models

Tellez, N.; Serra, Jean; Kumar, Y.; Li, J. J.; Morreale, Patricia

doi:10.1007/978-3-031-16075-2_11

Cited by 10 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further understand the model, the researchers then proceeded with bias analyses. The analysis was built upon previously developed strategies and applied to Meta's DETR transformer families [55,56].…”

Section: Model Trainingmentioning

confidence: 99%

Applying Swin Architecture to Diverse Sign Language Datasets

Kumar,

Huang,

Lin

et al. 2024

Electronics

View full text Add to dashboard Cite

In an era where artificial intelligence (AI) bridges crucial communication gaps, this study extends AI’s utility to American and Taiwan Sign Language (ASL and TSL) communities through advanced models like the hierarchical vision transformer with shifted windows (Swin). This research evaluates Swin’s adaptability across sign languages, aiming for a universal platform for the unvoiced. Utilizing deep learning and transformer technologies, it has developed prototypes for ASL-to-English translation, supported by an educational framework to facilitate learning and comprehension, with the intention to include more languages in the future. This study highlights the efficacy of the Swin model, along with other models such as the vision transformer with deformable attention (DAT), ResNet-50, and VGG-16, in ASL recognition. The Swin model’s accuracy across various datasets underscore its potential. Additionally, this research explores the challenges of balancing accuracy with the need for real-time, portable language recognition capabilities and introduces the use of cutting-edge transformer models like Swin, DAT, and video Swin transformers for diverse datasets in sign language recognition. This study explores the integration of multimodality and large language models (LLMs) to promote global inclusivity. Future efforts will focus on enhancing these models and expanding their linguistic reach, with an emphasis on real-time translation applications and educational frameworks. These achievements not only advance the technology of sign language recognition but also provide more effective communication tools for the deaf and hard-of-hearing community.

show abstract

Section: Model Trainingmentioning

confidence: 99%

Applying Swin Architecture to Diverse Sign Language Datasets

Kumar,

Huang,

Lin

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Huang et al's work on breast cancer using transformers adds valuable insights into early detection methods [14][15]. Addressing bias in Transformers, crucial across neural networks, has been intensively tackled with models like DETR and Deformable DETR [16][17][18]. Kumar et al's testFAILS framework guides responsible LLM apps [19].…”

Section: Related Workmentioning

confidence: 99%

Transformers and LLMs as the New Benchmark in Early Cancer Detection

Kumar,

Huang,

Gordon

et al. 2024

ITM Web Conf.

View full text Add to dashboard Cite

The study explores the transformative capabilities of Transformers and Large Language Models (LLMs) in the early detection of Acute Lymphoblastic Leukaemia (ALL). The researchers benchmark Vision Transformers with Deformable Attention (DAT) and Hierarchical Vision Transformers (Swin) against established Convolutional Neural Networks (CNNs) like ResNet-50 and VGG-16. The findings reveal that transformer models exhibit remarkable accuracy in identifying ALL from original images, demonstrating efficiency in image analysis without necessitating labour-intensive segmentation. A thorough bias analysis is conducted to ensure the robustness and fairness of the models. The promising performance of the transformer models indicates a trajectory towards surpassing CNNs in cancer detection, setting new standards for accuracy. In addition, the study explores the capabilities of LLMs in revolutionising early cancer detection and providing comprehensive support to ALL patients. These models assist in symptom analysis, offer preliminary assessments, and guide individuals seeking information, contributing to a more accessible and informed healthcare journey. The integration of these advanced AI technologies holds the potential to enhance early detection, improve patient outcomes, and reduce healthcare disparities, marking a significant advancement in the fight against ALL.

show abstract

“…Research on chatbot evaluation capitalizes on a profound background in Natural Language Processing (NLP) and an all-encompassing understanding of AI models, particularly within the Python programming ecosystem [13,14]. Recently, focus has veered towards Transformer Neural Networks, with the aim of unearthing and comprehending the biases embedded within their computational layers [15,16]. The emergence of Transformer Neural Networks has been recognized as a new frontier in both natural language processing and computer vision.…”

Section: Research Background and Related Workmentioning

confidence: 99%

A Testing Framework for AI Linguistic Systems (testFAILS)

Kumar,

Morreale,

Sorial

et al. 2023

Electronics

View full text Add to dashboard Cite

This paper presents an innovative testing framework, testFAILS, designed for the rigorous evaluation of AI Linguistic Systems (AILS), with particular emphasis on the various iterations of ChatGPT. Leveraging orthogonal array coverage, this framework provides a robust mechanism for assessing AI systems, addressing the critical question, “How should AI be evaluated?” While the Turing test has traditionally been the benchmark for AI evaluation, it is argued that current, publicly available chatbots, despite their rapid advancements, have yet to meet this standard. However, the pace of progress suggests that achieving Turing-test-level performance may be imminent. In the interim, the need for effective AI evaluation and testing methodologies remains paramount. Ongoing research has already validated several versions of ChatGPT, and comprehensive testing on the latest models, including ChatGPT-4, Bard, Bing Bot, and the LLaMA and PaLM 2 models, is currently being conducted. The testFAILS framework is designed to be adaptable, ready to evaluate new chatbot versions as they are released. Additionally, available chatbot APIs have been tested and applications have been developed, one of them being AIDoctor, presented in this paper, which utilizes the ChatGPT-4 model and Microsoft Azure AI technologies.

show abstract

Gauging Biases in Various Deep Learning AI Models

Cited by 10 publications

References 12 publications

Applying Swin Architecture to Diverse Sign Language Datasets

Applying Swin Architecture to Diverse Sign Language Datasets

Transformers and LLMs as the New Benchmark in Early Cancer Detection

A Testing Framework for AI Linguistic Systems (testFAILS)

Contact Info

Product

Resources

About