The Mechanical Neural Network(MNN) -- A physical implementation of a multilayer perceptron for education and hands-on experimentation
This provides a hands-on educational tool for students to understand neural networks, but it is incremental as it applies existing MLP concepts in a physical form without advancing computational methods.
The authors introduced a physical implementation of a multilayer perceptron (MLP) called the Mechanical Neural Network (MNN), designed for educational purposes to allow students to manually adjust weights and observe effects on outputs, such as modeling functions and logical operators like XOR.
In this paper the Mechanical Neural Network(MNN) is introduced, a physical implementation of a multilayer perceptron(MLP) with ReLU activation functions, two input neurons, four hidden neurons and two output neurons. This physical model of a MLP is used in education to give a hands on experience and allow students to experience the effect of changing the parameters of the network on the output. Neurons are small wooden levers which are connected by threads. Students can adapt the weights between the neurons by moving the clamps connecting a neuron via a thread to the next. The MNN can model real valued functions and logical operators including XOR.