Related papers: Jointly-Learned Exit and Inference for a Dynamic N…
Collaborative inference systems are one of the emerging solutions for deploying deep neural networks (DNNs) at the wireless network edge. Their main idea is to divide a DNN into two parts, where the first is shallow enough to be reliably…
Deep neural networks have become larger over the years with increasing demand of computational resources for inference; incurring exacerbate costs and leaving little room for deployment on devices with limited battery and other resources…
Early-exit neural networks (EENNs) enable adaptive and efficient inference by providing predictions at multiple stages during the forward pass. In safety-critical applications, these predictions are meaningful only when accompanied by…
Deep neural network (DNN) models are increasingly popular in edge video analytic applications. However, the compute-intensive nature of DNN models pose challenges for energy-efficient inference on resource-constrained edge devices. Most…
Deploying large language model inference remains challenging due to their high computational overhead. Early exit optimizes model inference by adaptively reducing the number of inference layers. Current methods typically train internal…
Deep neural network (DNN) based approaches hold significant potential for reinforcement learning (RL) and have already shown remarkable gains over state-of-art methods in a number of applications. The effectiveness of DNN methods can be…
Automatic modulation classification (AMC) plays a critical role in wireless communications by autonomously classifying signals transmitted over the radio spectrum. Deep learning (DL) techniques are increasingly being used for AMC due to…
Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint training often leads to gradient interference, with deeper classifiers dominating optimization. We propose…
Early-exit deep neural networks enable adaptive inference by terminating computation when sufficient confidence is achieved, reducing cost for edge AI accelerators in resource-constrained settings. Existing methods, however, rely on…
The limitations of unimodal deep learning models, particularly their tendency to overfit and limited generalizability, have renewed interest in multimodal fusion strategies. Multimodal deep neural networks (MDNN) have the capability of…
Critical transitions are the abrupt shifts between qualitatively different states of a system, and they are crucial to understanding tipping points in complex dynamical systems across ecology, climate science, and biology. Detecting these…
Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data. The ability to better predict GE based on a single training set may yield overarching DNN…
Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the…
Adversarial attacks have rendered high security risks on modern deep learning systems. Adversarial training can significantly enhance the robustness of neural network models by suppressing the non-robust features. However, the models often…
Early Exit Neural Networks (EENNs) endow astandard Deep Neural Network (DNN) with Early Exit Classifiers (EECs), to provide predictions at intermediate points of the processing when enough confidence in classification is achieved. This…
With deep neural networks (DNNs) emerging as the backbone in a multitude of computer vision tasks, their adoption in real-world applications broadens continuously. Given the abundance and omnipresence of smart devices in the consumer…
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…
Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously…
Edge offloading for deep neural networks (DNNs) can be adaptive to the input's complexity by using early-exit DNNs. These DNNs have side branches throughout their architecture, allowing the inference to end earlier in the edge. The branches…