Accelerated Artificial Neural Networks on FPGA for Fault Detection in Automotive Systems

Network Intrusion Detection Using Neural Networks on FPGA SoCs

“…Artificial Neural Networks (ANNs) are computational models inspired by human cognition, able to model complex nonlinear functions that correlate inputs and expected outputs. They have successfully been applied in a broad range of fields, from automotive [18], to healthcare [19]. Each artificial neuron calculates the weighted sum of its inputs and adds this to an offset value (bias), passing the result to an activation function.…”

Lightweight Programmable DSP Block Overlay for Streaming Neural Network Acceleration

“…We used the datasets and networks in Table I, trained using Tensorflow [10] to obtain the accuracies shown. These were chosen to represent a range of application domains and to match or exceed the complexity of NNs that have been more widely targetted for acceleration, for instance in [11] and [12]. The proposed overlay, designed for inference, does not implement an activation function at the output layer, since the required comparisons can be more flexibly made in software and raw outputs can used as feedback for fine-tuning.…”

Analysis of the RBF ANN-based classifier for the diagnostics of electronic circuit

“…Its only parameter is the threshold θ, below which two examples e i and e j are considered close to each other (2). The measure applied to create clusters exploits Euclidean d E (3) and cosine d c (4) distances, treating every example as the point in the m-dimensional space. This way groups located close to each other are easily identified.…”

“…Their numerous advantages include the ability to extract generalized knowledge from the available measurement data, autonomous operation (making them useful in the automated online diagnostics) and the ability to accurately process data in uncertainty conditions. Limited memory usage and high processing efficiency make them useful in embedded applications (implemented in the digital signal processor or the FPGA array [4]). Their disadvantage is the obscure form of stored knowledge (illegible for the human operator), making the explanation of generated decisions difficult.…”