Demystifying deep network architectures : from theory to applications

Deep neural networks significantly power the success of machine learning and artificial intelligence. Over the past decade, the community keeps designing architectures of deep layers and complicated connections. Many works in deep learning theory tried to understand deep networks from different perspectives and contributed to concrete analysis. However, the gap between deep learning theory and application is growingly large. Specifically, due to our partial understanding of our deep networks, current deep learning theory is not enough to guide us in designing practical neural architectures. This is mainly because of two gaps: 1) designing network architectures is very expensive, and 2) practical network architectures are much more complicated than what we studied in theory. Therefore, our core question to focus on is: how do we bridge these gaps, between deep learning theory and practical neural architecture designs? This dissertation will center around this challenge and tries to bridge the gap between the two worlds. First, current deep learning theory can inspire our architecture design (Chapter 3 and 4). We propose three theory-inspired indicators with strong correlations with networks' performance and they can be measured at networks' initialization without introducing any gradient descent cost. Based on these important metrics, we propose a training-free neural architecture design algorithm with extremely low computation and time costs. Second, the architecture design can further inspire deep learning theory (Chapter 5 and 6). By introducing two principled directions of the network's graph topology, we jointly analyze the impact of the network architecture on its convergence, expressivity, and generalization of networks, and demonstrate a "no free lunch" behavior in ReLU networks. Finally, a practical use case in the industry will be discussed (Chapter 7), where we design and scale up vision foundation models, again, without any training cost.

Name thesis:degree_name

Doctor of Philosophy

Level thesis:degree_level

Doctoral

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

The University of Texas at Austin

Year dc:date.issued

2023

Author dc:creator

• Chen, Wuyang

Advisor dc:contributor.advisor

• Wang, Zhangyang

Committee members dc:contributor.committeemember

• Bovik, Alan
• Hanin, Boris
• Kim, Hyeji
• Yu, Zhiding

• Deep learning
• Deep network architecture
• Neural architecture search
• Vision transformer
• Neural tangent kernel
• Linear region
• Jacobian
• Generalization

Language dc:language.iso

en

Identifier URI

http://dx.doi.org/10.26153/tsw/47362

OAI identifier oai:identifier

oai:repositories.lib.utexas.edu:2152/120500