Fig. 6
From: Contextual quantum neural networks for stock price prediction
Share-and-specify Ansatz. A diagram of our Quantum Multi-Task Learning Architecture showing various components for the QNN. A single asset state is loaded by setting the label \(\Big | k \Big \rangle\) and the inference-time context \(\varvec{x}^{(T)}\) is loaded over qubits \(\Big | 0 \Big \rangle ^{\otimes T+\tau }\). The input can then be processed through the parameterized circuit, composed of L layers of the share-and-specify ansatz, to define a state \(\Big | \varvec{y}^{(T)} \Big \rangle\) that can be utilized for a downstream task. For example, as depicted in the figure, measurement can be used to sample possible continuations \(x^{\tau }\).
