paper-with-me

홈 › Papers

ConCoDE: Hard-constrained Differentiable Co-Exploration Method for Neural Architectures and Hardware Accelerators

2021-09-29 · Deokki Hong, Kanghyun Choi, Hey Yoon Lee, Joonsang Yu, Youngsok Kim, Noseong Park, Jinho Lee

While DNNs achieve over-human performances in a number of areas, it is often accompanied by the skyrocketing computational costs. Co-exploration of an optimal neural architecture and its hardware accelerator is an approach of rising interest which addresses the computational cost problem, especially in low-profile systems (e.g., embedded, mobile). The difficulty of having to search the large co-exploration space is often addressed by adopting the idea of differentiable neural architecture search. Despite the superior search efficiency of the differentiable co-exploration, it faces a critical challenge of not being able to systematically satisfy hard constraints, such as frame rate or power budget. To handle the hard constraint problem of differentiable co-exploration, we propose ConCoDE, which searches for hard-constrained solutions without compromising the global design objectives. By manipulating the gradients in the interest of the given hard constraint, high-quality solutions satisfying the constraint can be obtained. Experimental results show that ConCoDE is able to meet the constraints even in tight conditions. We also show that the solutions searched by ConCoDE exhibit high quality compared to those searched without any constraint.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture Search

Similar Papers 제목 키워드 기반

Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Exploration

2023-01-23 · Deokki Hong, Kanghyun Choi, Hye Yoon Lee, Joonsang Yu 외

Co-exploration of an optimal neural architecture and its hardware accelerator is an approach of rising interest which addresses the computational cost problem, especially in low-profile systems. The large co-exploration …

Neural Architecture Search

DANCE: Differentiable Accelerator/Network Co-Exploration

2020-09-14 · Kanghyun Choi, Deokki Hong, Hojae Yoon, Joonsang Yu 외

To cope with the ever-increasing computational demand of the DNN execution, recent neural architecture search (NAS) algorithms consider hardware cost metrics into account, such as GPU latency. To further pursue a fast, e…

GPUNeural Architecture Search

HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search

2021-02-23 · Niv Nayman, Yonathan Aflalo, Asaf Noy, Lihi Zelnik-Manor

Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (…

Neural Architecture Search

Sample-Efficient Reinforcement Learning Controller for Deep Brain Stimulation in Parkinson's Disease

2025-07-08 · Harsh Ravivarapu, Gaurav Bagwe, Xiaoyong Yuan, Chunxiu Yu 외 arxiv

Deep brain stimulation (DBS) is an established intervention for Parkinson's disease (PD), but conventional open-loop systems lack adaptability, are energy-inefficient due to continuous stimulation, and provide limited pe…

Reinforcement Learning

SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video

2022-01-30 · CVPR 2022 1 · Boyi Jiang, Yang Hong, Hujun Bao, Juyong Zhang

We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods …

3D Human ReconstructionNeural Rendering