Related papers: Deep learning model compression using network sens…
As edge devices become prevalent, deploying Deep Neural Networks (DNN) on edge devices has become a critical issue. However, DNN requires a high computational resource which is rarely available for edge devices. To handle this, we propose a…
Deep Learning models have become the dominant approach in several areas due to their high performance. Unfortunately, the size and hence computational requirements of operating such models can be considerably high. Therefore, this…
Besides accuracy, the model size of convolutional neural networks (CNN) models is another important factor considering limited hardware resources in practical applications. For example, employing deep neural networks on mobile systems…
The deployment of deep neural networks on resource-constrained devices necessitates effective model com- pression strategies that judiciously balance the reduction of model size with the preservation of performance. This study introduces a…
WaveNet is a state-of-the-art text-to-speech vocoder that remains challenging to deploy due to its autoregressive loop. In this work we focus on ways to accelerate the original WaveNet architecture directly, as opposed to modifying the…
Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradients (IG) as a data augmentation strategy. Our approach…
Large neural networks require enormous computational clusters of machines. Model-parallel training, when the model architecture is partitioned sequentially between workers, is a popular approach for training modern models. Information…
Thanks to their state-of-the-art performance, deep neural networks are increasingly used for object recognition. To achieve these results, they use millions of parameters to be trained. However, when targeting embedded applications the size…
Deep learning models have achieved tremendous success in most of the industries in recent years. The evolution of these models has also led to an increase in the model size and energy requirement, making it difficult to deploy in production…
Deep neural networks (DNNs) continue to make significant advances, solving tasks from image classification to translation or reinforcement learning. One aspect of the field receiving considerable attention is efficiently executing deep…
Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…
Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently…
Model Compression has drawn much attention within the deep learning community recently. Compressing a dense neural network offers many advantages including lower computation cost, deployability to devices of limited storage and memories,…
The recent advances in machine learning and deep neural networks have made them attractive candidates for wireless communications functions such as channel estimation, decoding, and downlink channel state information (CSI) compression.…
This paper proposes \textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers. Layer fusion can significantly reduce…
Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory. Model compression methods address this…
Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted. Binary quantization obtains the highest compression but…
Complex neural networks require substantial memory to store a large number of synaptic weights. This work introduces WINGs (Automatic Weight Generator for Secure and Storage-Efficient Deep Learning Models), a novel framework that…
We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.…
Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them…