You must login before you can run this tool.
In recent years, parallel computing systems such as artificial neural networks (ANNs) have been of great interest. In these systems which emulate the behavior of human brains, the processing is carried out simultaneously. However, it is still a challenging engineering problem to design highly efficient hardware for parallel computing systems. Thus we want to investigate the possibility of computing using MEMS oscillators. In this tool, we write a class of oscillator network solver calculating the behaviors of each oscillator given initial conditions. We also simulate the application of pattern recognition and convolution based on the solver. Pattern recognition is accomplished using a model of Hopfield Network and convolution is possible using a Degree of Match function which defined as a function of state of network. The simulations results show that MEMS oscillator networks are able to memorize and recognize multiple patterns as well as perform image convolution with a structure consisting of a multitude of 2-oscillator networks. Hence, MEMS oscillator network is a potential candidate for future embedded computing system to improve computational performance of problems.
matplotlib; dataset in sklearn; numpy; scipy
Cite this work
Researchers should cite this work as follows: