An FPGA-friendly processing element based on the small logarithmic floating-point (SLFP) format is proposed. The proposed processing elements not only support inner product but also perform various nonlinear activation functions (NAF), which consume 674× LUT6s and 7× DSPs and operate at 450MHz in a pipeline manner for Zynq-7000. In addition, as the distribution of SLFP numbers is not uniform, this brief revises the weight decay scheme in the quantization aware training process to explore the optimum quantized weights. Compared with INT8 based design, the proposed method balances the resource usage between lookup tables and digital signal processing blocks. The accuracy loss of the quantized model based on the 8-bit SLFP is also small due to the high dynamic range of SLFP format. Moreover, since the proposed method can support different NAFs, this brief improves the quantized model accuracy by selecting an appropriate NAF from Swish, GELU, Mish and PReLU. Compared to the baseline (parameters are FP32, NAF is ReLU), the accuracy of quantized ResNet-50 and MobileNet is increased by 2.65% and -0.33%.

Discovering the causality from observational data is a crucial task in various scientific domains. With increasing awareness of privacy, data are not allowed to be exposed, and it is very hard to learn causal graphs from dispersed data, since these data may have different distributions. In this paper, we propose a federated causal discovery strategy (FedCausal) to learn the unified global causal graph from decentralized heterogeneous data. We design a global optimization formula to naturally aggregate the causal graphs from client data and constrain the acyclicity of the global graph without exposing local data. Unlike other federated causal learning algorithms, FedCausal unifies the local and global optimizations into a complete directed acyclic graph (DAG) learning process with a flexible optimization objective. We prove that this optimization objective has a high interpretability and can adaptively handle homogeneous and heterogeneous data. Experimental results on synthetic and real datasets show that FedCausal can effectively deal with non-independently and identically distributed (non-iid) data and has a superior performance.

Today’s mechatronic systems are becoming more and more complex as the development and design processes require collaboration across multiple engineering disciplines. The high complexity between loosely connected models results in a disconnect between these inter-disciplinary models, which may cause delays and costly rework in the long run. There is a need for an effective method to show the dependencies and risks across models for various stakeholder groups. Currently, the discussion about such methods is limited. This paper proposes and evaluates a user-friendly Decision Graph and Matrix Visualization method that combines network-based and matrix-based techniques to assist stakeholders in tracking dependencies and risks across models. The method is applied and demonstrated with a design and engineering case of a lab-scale production system, whose usability was tested formatively with experts.