1. Convolutional neural networks (CNNs) have become a popular approach in the field of artificial intelligence (AI).
2. This article proposes a comprehensive, step-by-step design procedure for a re-configurable CNN engine.
3. The proposed design layout occupies an area of 3.16 × 3.16 mm2 and achieved an accuracy of 96% for the Modified National Institute of Standards and Technology (MNIST) and Canadian Institute for Advanced Research (CIFAR-10) datasets.
The article is generally reliable and trustworthy, as it provides detailed information on the design procedure of a re-configurable convolutional neural network engine for FPGA-based applications. The authors provide evidence to support their claims, such as citing relevant literature and providing results from experiments conducted using the proposed design procedure. Furthermore, the authors provide a comprehensive overview of existing approaches to CNN implementation on FPGAs, which helps to contextualize their own work in this field.
However, there are some potential biases that should be noted in this article. For example, the authors focus primarily on the advantages of FPGA implementations over GPUs without exploring any potential drawbacks or counterarguments to this approach. Additionally, while the authors cite relevant literature throughout the article, they do not explore any alternative approaches or solutions that may exist in this field beyond those mentioned in their sources.
In conclusion, while this article is generally reliable and trustworthy due to its detailed information and evidence provided by the authors, there are some potential biases that should be noted when considering its content.