相关论文: ShuffleNet V2: Practical Guidelines for Efficient …

Recent advances in pruning of neural networks have made it possible to remove a large number of filters or weights without any perceptible drop in accuracy. The number of parameters and that of FLOPs are usually the reported metrics to…

One of the main barriers for deploying neural networks on embedded systems has been large memory and power consumption of existing neural networks. In this work, we introduce SqueezeNext, a new family of neural network architectures whose…

Though recent advanced convolutional neural networks (CNNs) have been improving the image recognition accuracy, the models are getting more complex and time-consuming. For real-world applications in industrial and commercial scenarios,…

Neural Networks (NN) provide a solid and reliable way of executing different types of applications, ranging from speech recognition to medical diagnosis, speeding up onerous and long workloads. The challenges involved in their…

In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-two weight representation and, as a result, performs only…

As cost and performance benefits associated with Moore's Law scaling slow, researchers are studying alternative architectures (e.g., based on analog and/or spiking circuits) and/or computational models (e.g., convolutional and recurrent…

We study how to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size). A simple and one-shot solution, named AutoSlim, is presented. Instead of…

Topologically interlocking architectures can generate tough ceramics with attractive thermo-mechanical properties. This concept can make the material design pathway a challenging task, since modeling the whole design space is neither…

Binarized Neural Network (BNN) removes bitwidth redundancy in classical CNN by using a single bit (-1/+1) for network parameters and intermediate representations, which has greatly reduced the off-chip data transfer and storage overhead.…

Expressivity plays a fundamental role in evaluating deep neural networks, and it is closely related to understanding the limit of performance improvement. In this paper, we propose a three-pipeline training framework based on critical…

We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost…

To reduce the computational cost of convolutional neural networks (CNNs) on resource-constrained devices, structured pruning approaches have shown promise in lowering floating-point operations (FLOPs) without substantial drops in accuracy.…

With the increasing popularity of deep learning, Convolutional Neural Networks (CNNs) have been widely applied in various domains, such as image classification and object detection, and achieve stunning success in terms of their high…

This paper proposes FractalNet, a framework based on fractal design principles that automatically generates and evaluates convolutional neural network (CNN) architectures using recursive template patterns. Rather than relying on…

Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts…

Modern CNN are typically based on floating point linear algebra based implementations. Recently, reduced precision NN have been gaining popularity as they require significantly less memory and computational resources compared to floating…

Automatic search of neural network architectures is a standing research topic. In addition to the fact that it presents a faster alternative to hand-designed architectures, it can improve their efficiency and for instance generate…

We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as…

Graph classification benchmarks, vital for assessing and developing graph neural networks (GNNs), have recently been scrutinized, as simple methods like MLPs have demonstrated comparable performance. This leads to an important question: Do…

Deep neural networks have seen tremendous success for different modalities of data including images, videos, and speech. This success has led to their deployment in mobile and embedded systems for real-time applications. However, making…