https://www.mdu.se/

Convolutional Neural Networks (CNNs) suffer from energy-hungry implementation due to requiring huge amounts of computations and significant memory consumption. This problem will be more highlighted by the proliferation of CNNs on resource-constrained platforms in, e.g., embedded systems. In this thesis, we focus on decreasing the computational cost of CNNs in order to be appropriate for resource-constrained platforms. The thesis work proposes two distinct methods to tackle the challenges: optimizing CNN architecture while considering network accuracy and network complexity, and proposing an optimized ternary neural network to compensate the accuracy loss of network quantization methods. We evaluated the impact of our solutions on Commercial-Off-The-Shelf (COTS) platforms where the results show considerable improvement in network accuracy and energy efficiency.

Convolutional Neural Networks (CNNs) lider av energihungriga implementationer på grund av att de kräver enorm beräkningskapacitet och har en betydande minneskonsumtion. Detta problem kommer att framhävas mer när allt fler CNN implementeras på resursbegränsade plattformar i inbyggda datorsystem. I denna uppsats fokuserar vi på att minska resursåtgången för CNN, i termer av behövda beräkningar och behövt minne, för att vara lämplig för resursbegränsade plattformar. Vi föreslår två metoder för att hantera utmaningarna; optimera CNN-arkitektur där man balanserar nätverksnoggrannhet och nätverkskomplexitet, och föreslår ett optimerat ternärt neuralt nätverk för att kompensera noggrannhetsförluster som kan uppstå vid nätverkskvantiseringsmetoder. Vi utvärderade effekterna av våra lösningar på kommersiellt använda plattformar (COTS) där resultaten visar betydande förbättringar i nätverksnoggrannhet och energieffektivitet.

Deep Neural Networks (DNNs) are increasingly being processed on resource-constrained edge nodes (computer nodes used in, e.g., cyber-physical systems or at the edge of computational clouds) due to efficiency, connectivity, and privacy concerns. This thesis investigates and presents new techniques to design and deploy DNNs for resource-constrained edge nodes. We have identified two major bottlenecks that hinder the proliferation of DNNs on edge nodes: (i) the significant computational demand for designing DNNs that consumes a low amount of resources in terms of energy, latency, and memory footprint; and (ii) further conserving resources by quantizing the numerical calculations of a DNN provides remarkable accuracy degradation.

To address (i), we present novel methods for cost-efficient Neural Architecture Search (NAS) to automate the design of DNNs that should meet multifaceted goals such as accuracy and hardware performance. To address (ii), we extend our NAS approach to handle the quantization of numerical calculations by using only the numbers -1, 0, and 1 (so-called ternary DNNs), which achieves higher accuracy. Our experimental evaluation shows that the proposed NAS approach can provide a 5.25x reduction in design time and up to 44.4x reduction in network size compared to state-of-the-art methods. In addition, the proposed quantization approach delivers 2.64% higher accuracy and 2.8x memory saving compared to full-precision counterparts with the same bit-width resolution. These benefits are attained over a wide range of commercial-off-the-shelf edge nodes showing this thesis successfully provides seamless deployment of DNNs on resource-constrained edge nodes.