Realizing number recognition with simulated quantum semi-restricted Boltzmann machine

Quantum machine learning based on quantum algorithms may achieve an exponential speedup over classical algorithms in dealing with some problems such as clustering. In this paper, we use the method of training the lower bound of the average log likelihood function on the quantum Boltzmann machine (QBM) to recognize the handwritten number datasets and compare the training results with classical models. We find that, when the QBM is semi-restricted, the training results get better with fewer computing resources. This shows that it is necessary to design a targeted algorithm to speed up computation and save resources.

Automated summary

In this paper, quantum machine learning based on quantum algorithms is used to recognize handwritten number datasets by training the quantum Boltzmann machine (QBM) and comparing the results with classical models. It is found that, when the QBM is semi-restricted, better training results are achieved with fewer computing resources. This highlights the importance of designing targeted algorithms for faster computation and resource conservation.