Related papers: Using Early Exits for Fast Inference in Automatic …

Modular Neural Networks (MNNs) demonstrate various advantages over monolithic models. Existing MNNs are generally $\textit{explicit}$: their modular architectures are pre-defined, with individual modules expected to implement distinct…

Supervised learning in machine learning (ML) requires labelled data set. Further real-time data classification requires an easily available methodology for labelling. Wireless modulation and signal classification find their application in…

Recently, deep neural networks have been outperforming conventional machine learning algorithms in many computer vision-related tasks. However, it is not computationally acceptable to implement these models on mobile and IoT devices and the…

Self-supervised speech models have shown to be useful for various tasks, but their large size limits the use in devices with low computing power and memory. In this work, we explore early exit, an approach for reducing latency by exiting…

The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy. This paper presents an optimization…

The real-time processing of time series signals is a critical issue for many real-life applications. The idea of real-time processing is especially important in audio domain as the human perception of sound is sensitive to any kind of…

Deep learning models that perform well often have high computational costs. In this paper, we combine two approaches that try to reduce the computational cost while keeping the model performance high: pruning and early exit networks. We…

Currently, it is a hot research topic to realize accurate, efficient, and real-time identification of massive spectral data with the help of deep learning and IoT technology. Deep neural networks played a key role in spectral analysis.…

Many real-world applications are widely adopting the edge computing paradigm due to its low latency and better privacy protection. With notable success in AI and deep learning (DL), edge devices and AI accelerators play a crucial role in…

Edge computing facilitates deep learning in resource-constrained environments, but challenges such as resource heterogeneity and dynamic constraints persist. This paper introduces AMP4EC, an Adaptive Model Partitioning framework designed to…

Automatic Modulation Recognition (AMR) is critical in identifying various modulation types in wireless communication systems. Recent advancements in deep learning have facilitated the integration of algorithms into AMR techniques. However,…

Transformer-based pre-trained language models (PLMs) mostly suffer from excessive overhead despite their advanced capacity. For resource-constrained devices, there is an urgent need for a spatially and temporally efficient model which…

Early exiting has become a promising approach to improving the inference efficiency of deep networks. By structuring models with multiple classifiers (exits), predictions for ``easy'' samples can be generated at earlier exits, negating the…

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…

Early-exit neural networks enable adaptive inference by allowing predictions at intermediate layers, reducing computational cost. However, early exits often lack interpretability and may focus on different features than deeper layers,…

As the next generation of mobile systems evolves, artificial intelligence (AI) is expected to deeply integrate with wireless communications for resource management in variable environments. In particular, deep reinforcement learning (DRL)…

As the development of lightweight deep learning algorithms, various deep neural network (DNN) models have been proposed for the remote sensing scene classification (RSSC) application. However, it is still challenging for these RSSC models…

Parameter-efficient transfer learning (PETL) has shown great potential in adapting a vision transformer (ViT) pre-trained on large-scale datasets to various downstream tasks. Existing studies primarily focus on minimizing the number of…

Modern search engine ranking pipelines are commonly based on large machine-learned ensembles of regression trees. We propose LEAR, a novel - learned - technique aimed to reduce the average number of trees traversed by documents to…

With the remarkable success achieved by the Convolutional Neural Networks (CNNs) in object recognition recently, deep learning is being widely used in the computer vision community. Deep Metric Learning (DML), integrating deep learning with…