QuasiNet: a neural network with trainable product layers
This work addresses the problem of improving neural network performance on hard logical problems for researchers and practitioners in machine learning, though it appears incremental as it builds on existing product neuron models.
The authors tackled the limited convergence of classical neural networks on hard problems like XOR and parity by proposing QuasiNet, a neural network with trainable product layers, which achieved a higher success rate than a classical multilayer perceptron in these tasks.
Classical neural networks achieve only limited convergence in hard problems such as XOR or parity when the number of hidden neurons is small. With the motivation to improve the success rate of neural networks in these problems, we propose a new neural network model inspired by existing neural network models with so called product neurons and a learning rule derived from classical error backpropagation, which elegantly solves the problem of mutually exclusive situations. Unlike existing product neurons, which have weights that are preset and not adaptable, our product layers of neurons also do learn. We tested the model and compared its success rate to a classical multilayer perceptron in the aforementioned problems as well as in other hard problems such as the two spirals. Our results indicate that our model is clearly more successful than the classical MLP and has the potential to be used in many tasks and applications.