An Analytic Framework for Robust Training of Artificial Neural Networks
The reliability of a learning model is key to the successful deployment of machine learning in various industries. Creating a robust model, particularly one unaffected by adversarial attacks, requires a comprehensive understanding of the adversarial examples phenomenon. However, it is difficult to describe the phenomenon due to the complicated nature of the problems in machine learning. Consequently, many studies investigate the phenomenon by proposing a simplified model of how adversarial examples occur and validate it by predicting some aspect of the phenomenon. While these studies cover many different characteristics of the adversarial examples, they have not reached a holistic approach to the geometric and analytic modeling of the phenomenon. This paper propose a formal framework to study the phenomenon in learning theory and make use of complex analysis and holomorphicity to offer a robust learning rule for artificial neural networks. With the help of complex analysis, we can effortlessly move between geometric and analytic perspectives of the phenomenon and offer further insights on the phenomenon by revealing its connection with harmonic functions. Using our model, we can explain some of the most intriguing characteristics of adversarial examples, including transferability of adversarial examples, and pave the way for novel approaches to mitigate the effects of the phenomenon.
Code (1)
Tasks
Learning TheorySimilar Papers 제목 키워드 기반
Reliable Fleet Analytics for Edge IoT Solutions
In recent years we have witnessed a boom in Internet of Things (IoT) device deployments, which has resulted in big data and demand for low-latency communication. This shift in the demand for infrastructure is also enabli…
BIG-bench Machine LearningDecision MakingEdge-computingTime Series AnalysisBenchmarking Reasoning Reliability in Artificial Intelligence Models for Energy-System Analysis
Artificial intelligence and machine learning are increasingly used for forecasting, optimization, and policy design in the energy sector, yet no standardized framework exists to evaluate whether these systems reason corr…
Computational EfficiencyMultilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience
As deep learning systems are scaled up to many billions of parameters, relating their internal structure to external behaviors becomes very challenging. Although daunting, this problem is not new: Neuroscientists and cog…
Critical Learning Periods Emerge Even in Deep Linear Networks
Critical learning periods are periods early in development where temporary sensory deficits can have a permanent effect on behavior and learned representations. Despite the radical differences between biological and arti…
Multi-Task LearningDesign of a dynamic and self adapting system, supported with artificial intelligence, machine learning and real time intelligence for predictive cyber risk analytics in extreme environments, cyber risk in the colonisation of Mars
Multiple governmental agencies and private organisations have made commitments for the colonisation of Mars. Such colonisation requires complex systems and infrastructure that could be very costly to repair or replace in…
Anomaly DetectionBIG-bench Machine LearningEdge-computing