相关论文: NaN-Propagation: A Novel Method for Sparsity Detec…

As a new programming paradigm, deep neural networks (DNNs) have been increasingly deployed in practice, but the lack of robustness hinders their applications in safety-critical domains. While there are techniques for verifying DNNs with…

High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them out-of-the-box to their own problems, albeit its purpose is…

Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-wise sparsification framework that leverages sensitivity…

Bit-level sparsity methods skip ineffectual zero-bit operations and are typically applicable within bit-serial deep learning accelerators. This type of sparsity at the bit-level is especially interesting because it is both orthogonal and…

Spiking Neural Networks (SNNs) are highly regarded for their energy efficiency, inherent activation sparsity, and suitability for real-time processing in edge devices. However, most current SNN methods adopt architectures resembling…

The emergence of neural architecture search (NAS) has greatly advanced the research on network design. Recent proposals such as gradient-based methods or one-shot approaches significantly boost the efficiency of NAS. In this paper, we…

Spiking Neural Networks (SNNs) have attracted great attention for their energy-efficient operations and biologically inspired structures, offering potential advantages over Artificial Neural Networks (ANNs) in terms of energy efficiency and…

Generative neural image compression supports data representation at extremely low bitrate, synthesizing details at the client and consistently producing highly realistic images. By leveraging the similarities between quantization error and…

We consider the problem of identifying a pattern of faults from a set of noisy linear measurements. Unfortunately, maximum a posteriori probability estimation of the fault pattern is computationally intractable. To solve the fault…

Neural network models are widely used in solving many challenging problems, such as computer vision, personalized recommendation, and natural language processing. Those models are very computationally intensive and reach the hardware limit…

We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We leverage weight normalization as a means of constraining parameters during…

Gradient sparsification is a communication optimisation technique for scaling and accelerating distributed deep neural network (DNN) training. It reduces the increasing communication traffic for gradient aggregation. However, existing…

Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by the out-of-distribution (OOD) extrapolation problem. Existing approaches typically…

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse…

Modern day engineering problems are ubiquitously characterized by sophisticated computer codes that map parameters or inputs to an underlying physical process. In other situations, experimental setups are used to model the physical process…

Reduced precision computation for deep neural networks is one of the key areas addressing the widening compute gap driven by an exponential growth in model size. In recent years, deep learning training has largely migrated to 16-bit…

The latest advances in deep learning have facilitated the development of highly accurate monocular depth estimation models. However, when training a monocular depth estimation network, practitioners and researchers have observed not a…

Neural Architecture Search (NAS) has been widely studied for designing discriminative deep learning models such as image classification, object detection, and semantic segmentation. As a large number of priors have been obtained through the…

Accurate surface roughness prediction is critical for ensuring high product quality, especially in areas like manufacturing and aerospace, where the smallest imperfections can compromise performance or safety. However, this is challenging…

In recent years, many neural network models have been proposed for pattern classification, function approximation and regression problems. This paper presents an approach for classifying patterns from simplified NNs. Although the predictive…