Towards Systems Education for Artificial Intelligence: A Course Practice in Intelligent Computing Architectures
Project Overview
The document highlights the significance of integrating artificial intelligence (AI) education with computing systems to create a comprehensive curriculum that blends system-level knowledge with AI algorithm training. It introduces a course on Intelligent Computing Architectures, which focuses on the design of AI accelerators using FPGA platforms, aiming to equip students with full-stack development skills that align with industry needs. Through practical labs and projects, the course enhances student engagement and provides hands-on experience in AI system design. The findings indicate that such an approach not only addresses the skills gap in the workforce but also fosters innovative thinking and problem-solving among students. Overall, the document underscores the transformative potential of generative AI in education by emphasizing practical applications and outcomes that prepare learners for future technological challenges.
Key Applications
Intelligent Computing Architectures course
Context: Higher education for students studying AI and computing systems
Implementation: Course including lectures, labs, and projects focusing on hardware and software co-design
Outcomes: Enhanced understanding of AI system design, practical skills in hardware implementation, and improved student engagement
Challenges: Heavy workloads, difficulties in timing optimization and software-hardware co-design for some students
Implementation Barriers
Curricular barrier
Existing curricula are outdated and do not adequately prepare students for industry needs in AI and computing systems.
Proposed Solutions: Introduce updated courses that integrate AI and computing system education.
Workload barrier
Students face heavy workloads which can be overwhelming and hinder their learning experience.
Proposed Solutions: Suggest improving FPGA skills in prior courses and adjust course workloads.
Skill barrier
Students may lack the necessary background in system capabilities, hardware design, and foundational knowledge.
Proposed Solutions: Provide prerequisites and foundational courses to better prepare students.
Project Team
Jianlei Yang
Researcher
Xiaopeng Gao
Researcher
Weisheng Zhao
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Jianlei Yang, Xiaopeng Gao, Weisheng Zhao
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai