Web Neural Network with Complete DiGraphs
This is an incremental improvement for neural network architecture research, aiming to better emulate brain-like processing.
The paper tackles the problem of neural networks not closely mimicking biological brain structure by proposing a complete directed graph model with cycles and continuous processing, which learns classification processes rather than just final results.
This paper introduces a new neural network model that aims to mimic the biological brain more closely by structuring the network as a complete directed graph that processes continuous data for each timestep. Current neural networks have structures that vaguely mimic the brain structure, such as neurons, convolutions, and recurrence. The model proposed in this paper adds additional structural properties by introducing cycles into the neuron connections and removing the sequential nature commonly seen in other network layers. Furthermore, the model has continuous input and output, inspired by spiking neural networks, which allows the network to learn a process of classification, rather than simply returning the final result.