… computations during inference with DeepLearning models. … needed by multiplications during inference can be potentially … energy efficiency for inference with DeepLearning Networks. …
J Soifer, J Li, M Li, J Zhu, Y Li, Y He, E Zheng… - … Machine Learning …, 2019 - usenix.org
… This paper introduces the DeepLearningInference Service, an online production service at … -latency deep neural network model inference. We present the system architecture and deep …
… Here, we present a deeplearning method for gene expression inference (D-GEX). D-GEX is … different strategies and tried to interpret the advantages of deeplearning compared with LR. …
… We study the accuracy and behavior of deeplearning networks when applied to type inference across a range of metrics (see Section 4.4). Our proposed model enhances a …
MMH Shuvo, SK Islam, J Cheng… - Proceedings of the …, 2022 - ieeexplore.ieee.org
Successful integration of deep neural networks (DNNs) or deeplearning (DL) has resulted in breakthroughs in many areas. However, deploying these highly accurate models for data-…
… to high-performance DNN inference algorithms has not been … inference accelerators as semiconductor scaling slows. This paper presents Simba, a scalable deep-learninginference ac…
… The application of deeplearning techniques resulted in remarkable improvement of machine learning models. In this paper we provide detailed characterizations of deeplearning …
Y Hu, R Ghosh, R Govindan - Proceedings of the ACM Symposium on …, 2021 - dl.acm.org
… In the paper, we presented a cost-efficient deeplearning inference system named Scrooge, which packs DL workload efficiently to maximize inference throughput while satisfying DL …
H Wu, P Judd, X Zhang, M Isaev… - arXiv preprint arXiv …, 2020 - arxiv.org
… the computational performance of deeplearning applications. It is … Once trained, neural networks can be deployed for inference … quantization for neural network inference, where trained …