NEURAL ARCHITECTURE SEARCH FOR EFFICIENT AI MODELS: A COMP REHENSIVE ANALYSIS
Ahmed Raza · Computer Science Bulletin · 2018
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Computer Science Bulletin · OpenAlex · article · 2018
Abstract
The surge in artificial intelligence (AI) applications has accentuated the need for efficient model architectures capable of delivering optimal performance with minimal computational resources. Neural Architecture Search (NAS) has emerged as a promising approach to automate the design of AI models tailored to specific tasks and hardware constraints. This article provides a comprehensive analysis of NAS methodologies, emphasizing their application in designing efficient AI models. We explore the latest advancements, challenges, and future directions, with particular focus on reinforcement learning, evolutionary algorithms, and gradient-based methods in NAS.
Case studies highlight the practical implications of NAS in real-world scenarios.
Open the resolved locator · 10.71465/csb2
Metadata licence: OpenAlex metadata (CC0)