Related papers: Late Breaking Results: Leveraging Approximate Comp…

We propose an optimization method for the automatic design of approximate multipliers, which minimizes the average error according to the operand distributions. Our multiplier achieves up to 50.24% higher accuracy than the best reproduced…

Customized hardware accelerators have been developed to provide improved performance and efficiency for DNN inference and training. However, the existing hardware accelerators may not always be suitable for handling various DNN models as…

Accelerating the inference of a trained DNN is a well studied subject. In this paper we switch the focus to the training of DNNs. The training phase is compute intensive, demands complicated data communication, and contains multiple levels…

DNN inference, known for its significant energy consumption and the resulting high carbon footprint, can be made more sustainable by adapting model size and accuracy to the varying carbon intensity throughout the day. Our heuristic…

Energy efficiency of hardware accelerators of deep neural networks (DNN) can be improved by introducing approximate arithmetic circuits. In order to quantify the error introduced by using these circuits and avoid the expensive hardware…

In this article, we investigate the impact of architectural parameters of array-based DNN accelerators on accelerator's energy consumption and performance in a wide variety of network topologies. For this purpose, we have developed a tool…

Deep Learning, and in particular, Deep Neural Network (DNN) is nowadays widely used in many scenarios, including safety-critical applications such as autonomous driving. In this context, besides energy efficiency and performance,…

Current state-of-the-art employs approximate multipliers to address the highly increased power demands of DNN accelerators. However, evaluating the accuracy of approximate DNNs is cumbersome due to the lack of adequate support for…

New directions in computing and algorithms has lead to some new applications that have tolerance to imprecision. Although, These applications are creating large volumes of data which exceeds the capability of today's computing systems.…

The rapid growth of resource-constrained mobile platforms, including mobile robots, wearable systems, and Internet-of-Things devices, has increased the demand for computationally efficient neural network controllers (NNCs) that can operate…

Given the stringent requirements of energy efficiency for Internet-of-Things edge devices, approximate multipliers, as a basic component of many processors and accelerators, have been constantly proposed and studied for decades, especially…

To speedup Deep Neural Networks (DNN) accelerator design and enable effective implementation, we propose HybridDNN, a framework for building high-performance hybrid DNN accelerators and delivering FPGA-based hardware implementations. Novel…

Deep Neural Networks (DNNs), as a subset of Machine Learning (ML) techniques, entail that real-world data can be learned and that decisions can be made in real-time. However, their wide adoption is hindered by a number of software and…

In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or…

Acceleration of Convolutional Neural Network (CNN) on edge devices has recently achieved a remarkable performance in image classification and object detection applications. This paper proposes an efficient and scalable CNN-based SoC-FPGA…

Parameterizable machine learning (ML) accelerators are the product of recent breakthroughs in ML. To fully enable their design space exploration (DSE), we propose a physical-design-driven, learning-based prediction framework for…

We show that DNN accelerator micro-architectures and their program mappings represent specific choices of loop order and hardware parallelism for computing the seven nested loops of DNNs, which enables us to create a formal taxonomy of all…

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…

Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep shift neural networks (DSNNs) offer a…

Provisioning dynamic machine learning (ML) inference as a service for artificial intelligence (AI) applications of edge devices faces many challenges, including the trade-off among accuracy loss, carbon emission, and unknown future costs.…