Comparison of Attention Models and Post-hoc Explanation Methods for Embryo Stage Identification: A Case Study

Gomez, Tristan; Fréour, Thomas; Mouchère, Harold

doi:10.1007/978-3-031-37731-0_17

Cited by 2 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of artificial intelligence-generated works (AGW), the current copyright law has limitations in protecting AGW due to its difficulty in distinguishing them from human creations [42]. In the In Vitro Fertilization (IVF) field, the black-box nature of deep learning models hinders their interpretability and raises fairness concerns [43]. Objective faithfulness metrics have been proposed to evaluate explanation methods, but their application shows low agreement on model ranking [44].…”

Section: Limitations and Potential Ethical Implications Of Relying On...mentioning

confidence: 99%

A Comparative Analysis of Generative Artificial Intelligence Tools for Natural Language Processing

Iorliam,

Ingio

2024

J. Comput. Theor. Appl.

View full text Add to dashboard Cite

Generative artificial intelligence tools have recently attracted a great deal of attention. This is because of their huge advantages, which include ease of usage, quick generation of answers to requests, and the human-like intelligence they possess. This paper presents a vivid comparative analysis of the top 9 generative artificial intelligence (AI) tools, namely ChatGPT, Perplexity AI, YouChat, ChatSonic, Google's Bard, Microsoft Bing Assistant, HuggingChat, Jasper AI, and Quora's Poe, paying attention to the Pros and Cons each of the AI tools presents. This comparative analysis shows that the generative AI tools have several Pros that outweigh the Cons. Further, we explore the transformative impact of generative AI in Natural Language Processing (NLP), focusing on its integration with search engines, privacy concerns, and ethical implications. A comparative analysis categorizes generative AI tools based on popularity and evaluates challenges in development, including data limitations and computational costs. The study highlights ethical considerations such as technology misuse and regulatory challenges. Additionally, we delved into AI Planning techniques in NLP, covering classical planning, probabilistic planning, hierarchical planning, temporal planning, knowledge-driven planning, and neural planning models. These planning approaches are vital in achieving specific goals in NLP tasks. In conclusion, we provide a concise overview of the current state of generative AI, including its challenges, ethical considerations, and potential applications, contributing to the academic discourse on human-computer interaction.

show abstract

Section: Limitations and Potential Ethical Implications Of Relying On...mentioning

confidence: 99%

A Comparative Analysis of Generative Artificial Intelligence Tools for Natural Language Processing

Iorliam,

Ingio

2024

J. Comput. Theor. Appl.

View full text Add to dashboard Cite

show abstract

“…Two studies compare two explainability methods, [39] (LIME vs Grad-CAM) and [21] (Bag-of-visual-words-based approach vs Grad-CAM). Only one thorough comparative study was found [17], in which nine different XAI methods, including five post-hoc ones, were evaluated using seven faithfulness metrics. This is, as well, the only study in which explainability methods are assessed through quality metrics such as the Increase in Confidence or the Average Drop [9].…”

Section: Limitations and Suggestionsmentioning

confidence: 99%

“…Another limitation in the field is privacy. None of the previous works makes the code (except for [4]) or the data (except for [17]) publicly available, making reproducibility impossible and replicability impractical. These flaws, in a task with a high degree of subjectivity (inter and intra-observer variability) induce a high risk of confirmation bias.…”

Section: Limitations and Suggestionsmentioning

confidence: 99%

Exploring the Role of Explainability in AI-Assisted Embryo Selection

Urcelay,

Hinjos,

Martin-Torres

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

In Vitro Fertilization is among the most widespread treatments for infertility. One of its main challenges is the evaluation and selection of embryo for implantation, a process with large inter- and intra-clinician variability. Deep learning based methods are gaining attention, but its opaque nature compromises their acceptance in the clinical context, where transparency in the decision making is key. In this paper we analyze the current work in the explainability of AI-assisted embryo analysis models, identifying the limitations. We also discuss how these models could be integrated in the clinical context as decision support systems, considering the needs of clinicians and patients. Finally, we propose guidelines for the sake of increasing interpretability and trustworthiness, pushing this technology forward towards established clinical practice.

show abstract

Comparison of Attention Models and Post-hoc Explanation Methods for Embryo Stage Identification: A Case Study

Cited by 2 publications

References 28 publications

A Comparative Analysis of Generative Artificial Intelligence Tools for Natural Language Processing

A Comparative Analysis of Generative Artificial Intelligence Tools for Natural Language Processing

Exploring the Role of Explainability in AI-Assisted Embryo Selection

Contact Info

Product

Resources

About