Related papers: HAPI: Hardware-Aware Progressive Inference
While the Internet of Things (IoT) technology is booming and offers huge opportunities for information exchange, it also faces unprecedented security challenges. As an important complement to the physical layer security technologies for…
In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essential building blocks…
For many practical applications, a high computational cost of inference over deep network architectures might be unacceptable. A small degradation in the overall inference accuracy might be a reasonable price to pay for a significant…
Convolutional Neural Networks (CNNs) have demonstrated exceptional performance in audio tagging tasks. However, deploying these models on resource-constrained devices like the Raspberry Pi poses challenges related to computational…
Convolutional Neural Networks (CNN) have been widely deployed in diverse application domains. There has been significant progress in accelerating both their training and inference using high-performance GPUs, FPGAs, and custom ASICs for…
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…
Efficient deployment of neural networks (NN) requires the co-optimization of accuracy and latency. For example, hardware-aware neural architecture search has been used to automatically find NN architectures that satisfy a latency constraint…
IoT Edge intelligence requires Convolutional Neural Network (CNN) inference to take place in the edge devices itself. ARM big.LITTLE architecture is at the heart of prevalent commercial edge devices. It comprises of single-ISA heterogeneous…
In recent years, convolutional neural networks (CNNs) have demonstrated their ability to solve problems in many fields and with accuracy that was not possible before. However, this comes with extensive computational requirements, which made…
Recently, the significant achievements have been made in skeleton-based human action recognition with the emergence of graph convolutional networks (GCNs). However, the state-of-the-art (SOTA) models used for this task focus on constructing…
As Convolutional Neural Networks (CNNs) are increasingly being employed in safety-critical applications, it is important that they behave reliably in the face of hardware errors. Transient hardware errors may percolate undesirable state…
Reducing inference time and energy usage while maintaining prediction accuracy has become a significant concern for deep neural networks (DNN) inference on resource-constrained edge devices. To address this problem, we propose a novel…
A lot of deep learning applications are desired to be run on mobile devices. Both accuracy and inference time are meaningful for a lot of them. While the number of FLOPs is usually used as a proxy for neural network latency, it may be not…
The Internet of Things is transforming various fields, with sensors increasingly embedded in wearables, smart buildings, and connected equipment. While deep learning enables valuable insights from IoT data, conventional models are too…
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.…
Early-exit mechanisms allow deep neural networks to stop inference once prediction confidence is high, reducing latency and energy on easy inputs while retaining full-depth accuracy on harder ones. Similarly, adding early exit mechanisms to…
Unlike machines, humans learn through rapid, abstract model-building. The role of a teacher is not simply to hammer home right or wrong answers, but rather to provide intuitive comments, comparisons, and explanations to a pupil. This is…
Deploying deep neural networks (DNNs) across homogeneous edge devices (the devices with the same SKU labeled by the manufacturer) often assumes identical performance among them. However, once a device model is widely deployed, the…
Though CNNs are highly parallel workloads, in the absence of efficient on-chip memory reuse techniques, an accelerator for them quickly becomes memory bound. In this paper, we propose a CNN accelerator design for inference that is able to…
Structural pruning can simplify network architecture and improve inference speed. We propose Hardware-Aware Latency Pruning (HALP) that formulates structural pruning as a global resource allocation optimization problem, aiming at maximizing…