QLattice Environment and Feyn QGraph Models—A New Perspective Toward Deep Learning
Vinayak Ashok Bharadi · 2021
Artificial neural networks (ANNs) have been with us for quite a time, and with the advancement in the technology, the availability of graphical processing unit (GPU) and tensor processing unit (TPU) advanced architectures has been in the reach of the common person. Deep neural networks are now playing a major role in pattern recognition. In this chapter, a new type of deep learning model is discussed, and they are called Feyn models under the QLattice environment. These are inspired by quantum mechanics; they extend the concept of photon movement to evaluate the best possible model for a given deep learning problem. It is based on the Feyn framework, which evaluates maximum possible models for a given type of problem, and then, the best model can be further selected and tested. The world is suffering from the COVID-19 outbreak, and daily, the COVID-19 impact data is released, and this data is used to train the QLattice models as a regression problem and predict the next impact estimate of the COVID-19 outbreak over the world. Further, the models are tested for binary classification problem for the prediction of a person is diabetic or not. The results show that the QLattice framework has a future in deep learning research.