Stochastic Configuration Machines: FPGA Implementation
This work addresses memory and resource constraints for industrial applications using neural networks, but it is incremental as it builds on existing stochastic configuration networks.
The paper tackled the problem of implementing stochastic configuration machines (SCMs) on FPGAs to reduce memory constraints and improve efficiency for industrial applications, achieving results on benchmark and industrial datasets with single-layer and deep architectures.
Neural networks for industrial applications generally have additional constraints such as response speed, memory size and power usage. Randomized learners can address some of these issues. However, hardware solutions can provide better resource reduction whilst maintaining the model's performance. Stochastic configuration networks (SCNs) are a prime choice in industrial applications due to their merits and feasibility for data modelling. Stochastic Configuration Machines (SCMs) extend this to focus on reducing the memory constraints by limiting the randomized weights to a binary value with a scalar for each node and using a mechanism model to improve the learning performance and result interpretability. This paper aims to implement SCM models on a field programmable gate array (FPGA) and introduce binary-coded inputs to the algorithm. Results are reported for two benchmark and two industrial datasets, including SCM with single-layer and deep architectures.