Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Real-time data analysis for medical diagnosis using FPGA-accelerated neural networks

Fig. 1

MLP models for (a) logical configuration and (b) compute. MLP models can have many layers, with each layer composed of potentially multiple neurons. Each neuron is connected to all neurons in the layer before it. The weights assigned to input connections of a single neuron are stored as a row vector, and every neuron has its own associated row vector. Combining row vectors of neurons in a layer forms the weight matrix for that particular layer. A non-linear function is applied to the weighted sum of a given neuron’s inputs, and the result forms the output of the neuron

Back to article page