Deep convolutional neural networks (CNNs) are computationally and memory intensive. In CNNs, intensive multiplication can have resource implications that may challenge the ability for effective deployment of inference on resource-constrained edge devices. This paper proposes GhostShiftAddNet, where the motivation is to implement a hardware-efficient deep network: a multiplication-free CNN with fewer redundant features. We introduce a new bottleneck block, GhostSA, that converts all multiplications in the block to cheap operations. The bottleneck uses an appropriate number of bit-shift filters to process intrinsic feature maps, then applies a series of transformations that consist of bit-wise shifts with addition operations to generate more feature maps that fully learn to capture information underlying intrinsic features. We schedule the number of bit-shift and addition operations for different hardware platforms. We conduct extensive experiments and ablation studies with desktop and embedded (Jetson Nano) devices for implementation and measurements. We demonstrate the proposed GhostSA block can replace bottleneck blocks in the backbone of state-of-the-art networks architectures and gives improved performance on image classification benchmarks. Further, our GhostShiftAddNet can achieve higher classification accuracy with fewer FLOPs and parameters (reduced by up to 3x) than GhostNet. When compared to GhostNet, inference latency on the Jetson Nano is improved by 1.3x and 2x on the GPU and CPU respectively. Code is available open-source on \url{https://github.com/JIABI/GhostShiftAddNet}.
Predicting Delayed Train Trajectories on the Dutch Railway Network: Explainable AI Evaluation of Topological, Operational and Weather Features with Tree Based Ensemble Methods
Morphological Operation Residual Blocks: Enhancing 3D Morphological Feature Representation in Convolutional Neural Networks for Semantic Segmentation of Medical Images
Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Paradigm. Inc.（第四范式有限公司）；Lenovo（联想）
Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey
CISTER - Research Centre in Real-Time and Embedded Computing Systems（CISTER实时与嵌入式计算系统研究中心）；The Hong Kong Polytechnic University（香港理工大学）；Commonwealth Scientific and Industrial Research Organization (CSIRO)（联邦科学与工业研究组织（CSIRO））；University of Manitoba（曼尼托巴大学）
Unleashing the potential of GNNs via Bi-directional Knowledge Transfer
Beijing Jiaotong University（北京交通大学）；Beijing Key Laboratory of Advanced Information Science and Network Technology（北京先进信息科学与网络技术重点实验室）；Qiyuan Lab（启元实验室）；Beihang University（北京航空航天大学）
Network On Network for Tabular Data Classification in Real-world Applications
Paradigm Inc.（第四范式公司）；Hong Kong University of Science and Technology（香港科技大学）
表格数据是我们的客户从零售、金融到电子商务最常用的数据格式，而表格数据分类对其业务起着至关重要的作用。在本文中，我们提出了Network On Network（NON），这是一种基于深度神经网络的实用表格数据分类模型，可提供准确的预测。人们提出了各种各样的深部探测方法，并取得了可喜的进展。然而，它们大多使用神经网络和因式分解机等操作来直接融合不同特征的嵌入，并将这些操作的输出线性组合以获得最终的预测。结果，场内信息和那些操作（例如，神经网络和因子分解机器）之间的非线性交互被忽略。场内信息是每个场内的特征属于同一场的信息。NON被提出来充分利用场内信息和非线性相互作用。它由三个部分组成：底层的逐场网络，用于捕获场内信息;中间的跨场网络，用于选择合适的操作数据驱动器;顶层的操作融合网络，用于对所选操作的输出进行深度融合。在六个真实世界数据集上的广泛实验表明，NON可以显着优于最先进的模型。此外，定性和定量的研究嵌入空间的特征表明，NON可以有效地捕捉场内信息。
