Related papers: Modeling Data Reuse in Deep Neural Networks by Tak…

Standardized DNN models that have been proved to perform well on machine learning tasks are widely used and often adopted as-is to solve downstream tasks, forming the transfer learning paradigm. However, when serving multiple instances of…

Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of these models. Previous efforts, including techniques like model…

Deep neural networks (DNNs) have revolutionized the field of artificial intelligence and have achieved unprecedented success in cognitive tasks such as image and speech recognition. Training of large DNNs, however, is computationally…

PPG-based Blood Pressure (BP) estimation is a challenging biosignal processing task for low-power devices such as wearables. State-of-the-art Deep Neural Networks (DNNs) trained for this task implement either a PPG-to-BP signal-to-signal…

Graph Neural Networks (GNNs) are powerful tools for processing graph-structured data, increasingly used for large-scale real-world graphs via sampling-based inference methods. However, inherent characteristics of neighbor sampling lead to…

Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its…

The rise of Deep Neural Networks (DNNs) has led to an increase in model size and complexity, straining the memory capacity of GPUs. Sparsity in DNNs, characterized as structural or ephemeral, has gained attention as a solution. This work…

Recently, deep neural networks (DNNs) have been widely applied in mobile intelligent applications. The inference for the DNNs is usually performed in the cloud. However, it leads to a large overhead of transmitting data via wireless…

In this paper, we present a novel technique to search for hardware architectures of accelerators optimized for end-to-end training of deep neural networks (DNNs). Our approach addresses both single-device and distributed pipeline and tensor…

Exploiting the great expressive power of Deep Neural Network architectures, relies on the ability to train them. While current theoretical work provides, mostly, results showing the hardness of this task, empirical evidence usually differs…

GPUs are used for training, inference, and tuning the machine learning models. However, Deep Neural Network (DNN) vary widely in their ability to exploit the full power of high-performance GPUs. Spatial sharing of GPU enables multiplexing…

Deep Neural Networks (DNN) have been successfully used to perform classification and regression tasks, particularly in computer vision based applications. Recently, owing to the widespread deployment of Internet of Things (IoT), we identify…

Compute-in-memory (CIM) has emerged as a pivotal direction for accelerating workloads in the field of machine learning, such as Deep Neural Networks (DNNs). However, the effective exploitation of sparsity in CIM systems presents numerous…

In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures. We propose a number of hypotheses on the effects of specific intermediate-layer…

How to reduce the requirement on training dataset size is a hot topic in deep learning community. One straightforward way is to reuse some pre-trained parameters. Some previous work like Deep transfer learning reuse the model parameters…

Distributed deep neural networks (DNNs) have emerged as a key technique to reduce communication overhead without sacrificing performance in edge computing systems. Recently, entropy coding has been introduced to further reduce the…

This is the 1st part of the dissertation for my master degree and compares the power consumption using the default floating point (32bit) and Nvidia mixed precision (16bit and 32bit) while training a classification ML model. A custom PC…

Deep neural network (DNN) inference in energy harvesting (EH) devices poses significant challenges due to resource constraints and frequent power interruptions. These power losses not only increase end-to-end latency, but also compromise…

This study is focused on determining the potential of using deep neural networks (DNNs) to predict the ultimate bearing capacity of shallow foundation in situations when the experimental data which may be used to train networks is scarce.…

This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices. However, harvested energy is usually weak and…