Enhancing LUT-based Deep Neural Networks Inference through Architecture and Connectivity Optimization
Deploying deep neural networks (DNNs) on resource-constrained edge devices such as FPGAs requires a careful balance among latency, power, and hardware resource usage, while maintaining high accuracy. Existing Lookup Table (LUT)-based DNNs -- such as LogicNets, PolyLUT, and NeuraLUT -- face two critical challenges: the exponential growth of LUT size and inefficient random sparse connectivity. This paper presents SparseLUT, a comprehensive framework that addresses these challenges through two orthogonal optimizations. First, we propose an architectural enhancement that aggregates multiple PolyLUT sub-neurons via an adder, significantly reducing LUT consumption by 2.0x-13.9x and lowering inference latency by 1.2x-1.6x, all while maintaining comparable accuracy. Building upon this foundation, we further introduce a non-greedy training algorithm that optimizes neuron connectivity by selectively pruning less significant inputs and strategically regrowing more effective ones. This training optimization, which incurs no additional area and latency overhead, delivers consistent accuracy improvements across benchmarks -- achieving up to a 2.13% gain on MNIST and 0.94% on Jet Substructure Classification compared to existing LUT-DNN approaches.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Robust Mode Connectivity-Oriented Adversarial Defense: Enhancing Neural Network Robustness Against Diversified $\ell_p$ Attacks
Adversarial robustness is a key concept in measuring the ability of neural networks to defend against adversarial attacks during the inference phase. Recent studies have shown that despite the success of improving advers…
Adversarial DefenseAdversarial RobustnessComputational EfficiencySelf-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural Networks
Inferring synaptic connectivity from neural population activity is a fundamental challenge in computational neuroscience, complicated by partial observability and mismatches between inference models and true circuit dyna…
Graph Neural NetworkOn Enhancing Network Throughput using Reinforcement Learning in Sliced Testbeds
Novel applications demand high throughput, low latency, and high reliability connectivity and still pose significant challenges to slicing orchestration architectures. The literature explores network slicing techniques t…
Combinatorial OptimizationReinforcement Learning (RL)An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruni…
Code GenerationCompiler OptimizationTransferring Social Network Knowledge from Multiple GNN Teachers to Kolmogorov-Arnold Networks
Graph Neural Networks (GNNs) have shown strong performance on graph-structured data, but their reliance on graph connectivity often limits scalability and efficiency. Kolmogorov-Arnold Networks (KANs), a recent architect…
Node Classification