相关论文: TanhExp: A Smooth Activation Function with High Co…

Convolutional neural networks are the most successful models in single image super-resolution. Deeper networks, residual connections, and attention mechanisms have further improved their performance. However, these strategies often improve…

Spiking Neural Networks (SNNs) are promising biologically plausible models of computation which utilize a spiking binary activation function similar to that of biological neurons. SNNs are well positioned to process spatiotemporal data, and…

Packet classification is a core function in software-defined networks, and learning-based methods have recently shown significant throughput gains on large-scale rulesets. However, existing learning-based approaches struggle with…

Conditional computation for Deep Neural Networks (DNNs) reduce overall computational load and improve model accuracy by running a subset of the network. In this work, we present a runtime throttleable neural network (TNN) that can…

A long-standing proposition is that by emulating the operation of the brain's neocortex, a spiking neural network (SNN) can achieve similar desirable features: flexible learning, speed, and efficiency. Temporal neural networks (TNNs) are…

Recent studies have demonstrated that the convolutional networks heavily rely on the quality and quantity of generated features. However, in lightweight networks, there are limited available feature information because these networks tend…

Convolutional Neural Networks are extensively used in a wide range of applications, commonly including computer vision tasks like image and video classification, recognition, and segmentation. Recent research results demonstrate that…

Prior work on probing neural networks primarily relies on input-space analysis or parameter perturbation, both of which face fundamental limitations in accessing structural information encoded in intermediate representations. We introduce…

Photo exposure correction is widely investigated, but fewer studies focus on correcting under- and over-exposed images simultaneously. Three issues remain open to handle and correct both under- and over-exposed images in a unified way.…

The simulation of human neurons and neurotransmission mechanisms has been realized in deep neural networks based on the theoretical implementations of activation functions. However, recent studies have reported that the threshold potential…

Deep Neural Networks have been shown to be beneficial for a variety of tasks, in particular allowing for end-to-end learning and reducing the requirement for manual design decisions. However, still many parameters have to be chosen in…

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.…

The driving force behind convolutional networks - the most successful deep learning architecture to date, is their expressive power. Despite its wide acceptance and vast empirical evidence, formal analyses supporting this belief are scarce.…

High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hindering their usage in latency-sensitive applications. As not…

Electroencephalography (EEG) offers non-invasive, real-time mental workload assessment, which is crucial in high-stakes domains like aviation and medicine and for advancing brain-computer interface (BCI) technologies. This study introduces…

One of the principal objectives of Natural Language Processing (NLP) is to generate meaningful representations from text. Improving the informativeness of the representations has led to a tremendous rise in the dimensionality and the memory…

The recent development of light-weighted neural networks has promoted the applications of deep learning under resource constraints and mobile applications. Many of these applications need to perform a real-time and efficient prediction for…

The design of energy-efficient, high-performance, and reliable Convolutional Neural Network (CNN) accelerators involves significant challenges due to complex power and thermal management issues. This paper introduces SAfEPaTh, a novel…

We propose $\textit{Mish}$, a novel self-regularized non-monotonic activation function which can be mathematically defined as: $f(x)=x\tanh(softplus(x))$. As activation functions play a crucial role in the performance and training dynamics…

Weight-sharing plays a significant role in the success of many deep neural networks, by increasing memory efficiency and incorporating useful inductive priors about the problem into the network. But understanding how weight-sharing can be…