Related papers: Deployment-Aligned Low-Precision Neural Architectu…
We implement a differentiable Neural Architecture Search (NAS) method inspired by FBNet for discovering neural networks that are heavily optimized for a particular target device. The FBNet NAS method discovers a neural network from a given…
To defend deep neural networks from adversarial attacks, adversarial training has been drawing increasing attention for its effectiveness. However, the accuracy and robustness resulting from the adversarial training are limited by the…
Recent advancements in artificial intelligence (AI) have positioned deep learning (DL) as a pivotal technology in fields like computer vision, data mining, and natural language processing. A critical factor in DL performance is the…
Efficient search is a core issue in Neural Architecture Search (NAS). It is difficult for conventional NAS algorithms to directly search the architectures on large-scale tasks like ImageNet. In general, the cost of GPU hours for NAS grows…
The significant computational cost of multiplications hinders the deployment of deep neural networks (DNNs) on edge devices. While multiplication-free models offer enhanced hardware efficiency, they typically sacrifice accuracy. As a…
In this paper, we present a novel multi-objective hardware-aware neural architecture search (NAS) framework, namely HSCoNAS, to automate the design of deep neural networks (DNNs) with high accuracy but low latency upon target hardware. To…
The ongoing advancements in network architecture design have led to remarkable achievements in deep learning across various challenging computer vision tasks. Meanwhile, the development of neural architecture search (NAS) has provided…
This paper introduces MARCO (Multi-Agent Reinforcement learning with Conformal Optimization), a novel hardware-aware framework for efficient neural architecture search (NAS) targeting resource-constrained edge devices. By significantly…
Edge computing aims to enable edge devices, such as IoT devices, to process data locally instead of relying on the cloud. However, deep learning techniques like computer vision and natural language processing can be computationally…
The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the substantial gap between performance requirements and available processing power. While recent research has made significant strides in developing pruning…
Neural architecture search (NAS) automates neural network design by using optimization algorithms to navigate architecture spaces, reducing the burden of manual architecture design. While NAS has achieved success, applying it to emerging…
Neural Architecture Search (NAS) has proven effective in discovering new Convolutional Neural Network (CNN) architectures, particularly for scenarios with well-defined accuracy optimization goals. However, previous approaches often involve…
Early neural network architectures were designed by so-called "grad student descent". Since then, the field of Neural Architecture Search (NAS) has developed with the goal of algorithmically designing architectures tailored for a dataset of…
The deep neural network (DNN) based AI applications on the edge require both low-cost computing platforms and high-quality services. However, the limited memory, computing resources, and power budget of the edge devices constrain the…
Neural architecture search (NAS) is a hard computationally expensive optimization problem with a discrete, vast, and spiky search space. One of the key research efforts dedicated to this space focuses on accelerating NAS via certain proxy…
To preserve user privacy while enabling mobile intelligence, techniques have been proposed to train deep neural networks on decentralized data. However, training over decentralized data makes the design of neural architecture quite…
Neural architecture search (NAS) aims to produce the optimal sparse solution from a high-dimensional space spanned by all candidate connections. Current gradient-based NAS methods commonly ignore the constraint of sparsity in the search…
Traditional neural architecture search (NAS) has a significant impact in computer vision by automatically designing network architectures for various tasks. In this paper, binarized neural architecture search (BNAS), with a search space of…
Compute In-Memory platforms such as memristive crossbars are gaining focus as they facilitate acceleration of Deep Neural Networks (DNNs) with high area and compute-efficiencies. However, the intrinsic non-idealities associated with the…
Hardware-Aware Neural Architecture Search (HW-NAS) requires joint optimization of accuracy and latency under device constraints. Traditional supernet-based methods require multiple GPU days per dataset. Large Language Model (LLM)-driven…