The Power of Generative AI: A Review of Requirements, Models, Input–Output Formats, Evaluation Metrics, and Challenges

Abstract

Generative artificial intelligence (AI) has emerged as a powerful technology with numerous applications in various domains. There is a need to identify the requirements and evaluation metrics for generative AI models designed for specific tasks. The purpose of the research aims to investigate the fundamental aspects of generative AI systems, including their requirements, models, input–output formats, and evaluation metrics. The study addresses key research questions and presents comprehensive insights to guide researchers, developers, and practitioners in the field. Firstly, the requirements necessary for implementing generative AI systems are examined and categorized into three distinct categories: hardware, software, and user experience. Furthermore, the study explores the different types of generative AI models described in the literature by presenting a taxonomy based on architectural characteristics, such as variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, transformers, language models, normalizing flow models, and hybrid models. A comprehensive classification of input and output formats used in generative AI systems is also provided. Moreover, the research proposes a classification system based on output types and discusses commonly used evaluation metrics in generative AI. The findings contribute to advancements in the field, enabling researchers, developers, and practitioners to effectively implement and evaluate generative AI models for various applications. The significance of the research lies in understanding that generative AI system requirements are crucial for effective planning, design, and optimal performance. A taxonomy of models aids in selecting suitable options and driving advancements. Classifying input–output formats enables leveraging diverse formats for customized systems, while evaluation metrics establish standardized methods to assess model quality and performance.

Exploring the transformative power of AI in art through a circular economy lens. A systematic literature review

“…The application of technology, big data, machine learning and AI in artistic works has intensified in recent times [ 18 ] promoting the autonomous process of content generation through AI. The changes introduced by AIGC generating synthetic data that resemble aspects of the real world [ 47 ]. AI can be used to create generative art based on these algorithms and automatic processes that produce works of art in constant change and evolution [ 48 ].…”

“…Generative content in art refers to art created by a system that operates autonomously [ 46 ]. AIGC develops algorithms and models capable of generating synthetic data that resemble aspects of the real world [ 47 ]. Programming and artificial intelligence can be used to create generative art based on these algorithms and automatic processes that produce works of art in constant change and evolution [ 48 ].…”

Integrating Deep Learning with Symbolic Reasoning in TinyLlama for Accurate Information Retrieval

“…Research has also focused on the use of symbolic AI in problem-solving and decision-making tasks, demonstrating its capability to handle complex, rule-based scenarios [42], [43], [44], [45], [6]. The potential of symbolic reasoning in enhancing the reliability and consistency of AI systems has been another area of interest, with studies aiming to create models that can consistently apply rules and logic [32], [46], [47]. Efforts have also been made to integrate symbolic reasoning in AI for educational purposes, particularly in developing intelligent tutoring systems that can adapt to the learning styles and needs of individual students [48], [49].…”

Transparency in Music-Generative AI: A Systematic Literature Review

“…Finally, it is also interesting to highlight the review presented in Bandi et al (2023), which is focused on the current state-of-the-art in generative AI, covering its requirements, models, input-output formats, and evaluation metrics. Besides providing a comprehensive and detailed study on these aspects, the authors highlight multiple challenges and implementation issues of generative AI.…”