Related papers: Optimization of Layer Skipping and Frequency Scali…
Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we leverage the intrinsic…
Deploying deep Convolutional Neural Networks (CNNs) is impacted by their memory footprint and speed requirements, which mainly come from convolution. Widely-used convolution algorithms, im2col and MEC, produce a lowered matrix from an…
Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…
Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources. In this paper, we reduce this cost by exploiting the fact that the importance of features computed by…
Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs in a wide range of situations, especially mobile…
Convolutional neural networks (CNNs) are reported to be overparametrized. The search for optimal (minimal) and sufficient architecture is an NP-hard problem as the hyperparameter space for possible network configurations is vast. Here, we…
Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is a vast demand for…
Deep neural networks for image super-resolution (SR) have demonstrated superior performance. However, the large memory and computation consumption hinders their deployment on resource-constrained devices. Binary neural networks (BNNs),…
Neural Networks are currently one of the most widely deployed machine learning algorithms. In particular, Convolutional Neural Networks (CNNs), are gaining popularity and are evaluated for deployment in safety critical applications such as…
Parameter-Efficient Fine-Tuning (PEFT) has become the standard for adapting large language models (LLMs). In this work we challenge the wide-spread assumption that parameter efficiency equates memory efficiency and on-device adaptability.…
Convolutional neural network (CNN) is one of the most widely-used successful architectures in the era of deep learning. However, the high-computational cost of CNN still hampers more universal uses to light devices. Fortunately, the Fourier…
Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT)…
Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networks. This paper proposes a novel method to reduce the…
Deep Convolutional Neural Networks (CNN) have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene label- ing, due to their large learning capacity and resistance to…
Spiking Neural Networks (SNNs) have recently gained significant interest in on-chip learning in embedded devices and emerged as an energy-efficient alternative to conventional Artificial Neural Networks (ANNs). However, to extend SNNs to a…
Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of these models. Previous efforts, including techniques like model…
To alleviate the shortage of computing power faced by clients in training deep neural networks (DNNs) using federated learning (FL), we leverage the edge computing and split learning to propose a model-splitting allowed FL (SFL) framework,…
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations. However, in the case of convolutional neural networks…
We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy but each image evaluation requires millions of floating point…
Although large-scale labeled data are essential for deep convolutional neural networks (ConvNets) to learn high-level semantic visual representations, it is time-consuming and impractical to collect and annotate large-scale datasets. A…