Select Page

Now this example is simple and has no QNNs. In general, steps of building and training QNNs would be simmilar to the building standard neural networks. Here they are: 1. Prepare Quantum Dataset - As with regular neural networks, we need to build dataset first. This is done by creating unparameterized cirq.Circuit objects and then injecting them into computation graph with tfq.convert_to_tensor. 2. Evaluate Quantum Model - In this step, we avaluate how well our quantum model is performing. It's main goal is to perform a quantum computation in order to extract information hidden in a quantum subspace. 3. Sample or Average - In this step we extract classical information in the forme of samples from a classical random variable. Quantum state and measured observable impact distribution values of this random variable. 4. Evaluate Classical Model - We use deep neural networks to distill correlations between measured expectations. 5. Evaluate Cost Function - Cost function is calculated and evaluated based on the results from the previous step. 6. Evaluate Gradients & Update Parameters - After evaluation