Based on What We Can Control Artificial Neural Networks
This work addresses the challenge of controlling and optimizing ANNs for researchers and practitioners, but it appears incremental as it applies existing control theory concepts to ANNs without demonstrating major breakthroughs.
The paper tackles the problem of ensuring stability and efficiency in Artificial Neural Networks (ANNs) by proposing a systematic analysis method based on control systems theory, which simulates system responses to factors like optimizers and hyperparameters, though no concrete numerical results are provided.
How can the stability and efficiency of Artificial Neural Networks (ANNs) be ensured through a systematic analysis method? This paper seeks to address that query. While numerous factors can influence the learning process of ANNs, utilizing knowledge from control systems allows us to analyze its system function and simulate system responses. Although the complexity of most ANNs is extremely high, we still can analyze each factor (e.g., optimiser, hyperparameters) by simulating their system response. This new method also can potentially benefit the development of new optimiser and learning system, especially when discerning which components adversely affect ANNs. Controlling ANNs can benefit from the design of optimiser and learning system, as (1) all optimisers act as controllers, (2) all learning systems operate as control systems with inputs and outputs, and (3) the optimiser should match the learning system. Please find codes: \url{https://github.com/RandomUserName2023/Control-ANNs}.