Efficient neural architectures for edge devices

The rise of IoT networks, with numerous interconnected edge devices, has led to an increase in demand for intelligent data processing closer to the data source. Deployment of neural networks at the edge is desirable, though challenging since an edge has limitations on available resources.
The focus of this thesis is on neural architectures for Convolutional Neural Networks (CNNs) that execute on the edge. The thesis presents Evolutionary Piecemeal Training (EPT), an algorithm for an efficient Neural Architecture Search (NAS). This flexible algorithm treats NAS as an optimization problem with a variable number of objectives possible. To highlight the versatility of EPT, three different sets of experiments have been shown in the thesis, with one, two and four objectives respectively. The multi-objective algorithm typically involves hardware specific objectives in addition to accuracy of the CNN to produce a pareto-optimal set of neural architectures.
Further, the thesis examines adaptivity of the CNN-based application running at the edge. The first work is Scenario Based Run-time Switching (SBRS) framework, where every scenario represents an operation mode and has an associated CNN. An application may switch between scenarios to allow synchronous adaptation with environmental changes. Additionally, a framework was presented to efficiently share and reuse CNNs in distributed IoT networks. This framework supports maintenance and adaptation of existing and deployed CNNs at the edge.
To conclude, this thesis demonstrates various methodologies to improve the performance of a CNN deployed on a resource-constrained edge device. The key ideas include searching for an efficient neural architecture, adaptive applications with run-time CNN switching and CNNs as dynamic entities in a distributed IoT network.