Exploring the Intersection between Neural Architecture Search and Continual Learning

Abstract

Despite the significant advances achieved in Artificial Neural Networks (ANNs), their design process remains notoriously tedious, depending primarily on intuition, experience and trial-and-error. This human-dependent process is often time-consuming and prone to errors. Furthermore, the models are generally bound to their training contexts, with no considerations to their surrounding environments. Continual adaptiveness and automation of neural networks is of paramount importance to several domains where model accessibility is limited after deployment (e.g IoT devices, self-driving vehicles, etc.). Additionally, even accessible models require frequent maintenance post-deployment to overcome issues such as Concept/Data Drift, which can be cumbersome and restrictive. By leveraging and combining approaches from Neural Architecture Search (NAS) and Continual Learning (CL), more robust and adaptive agents can be developed. This study conducts the first extensive review on the intersection between NAS and CL, formalizing the prospective Continually-Adaptive Neural Networks (CANNs) paradigm and outlining research directions for lifelong autonomous ANNs.

References in corpus (13)

• Distilling the Knowledge in a Neural Network
• Overcoming catastrophic forgetting in neural networks
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• AutoML: A Survey of the State-of-the-Art
• A continual learning survey: Defying forgetting in classification tasks
• A Survey on Evolutionary Neural Architecture Search
• A Survey on Neural Architecture Search
• Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
• Don't forget, there is more than forgetting: new metrics for Continual Learning
• BNAS:An Efficient Neural Architecture Search Approach Using Broad Scalable Architecture
• Architecture Matters in Continual Learning
• Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy
• Revisiting Neural Networks for Continual Learning: An Architectural Perspective