Quantum Neural Networks: Architectures and Training
Quantum neural network architectures and how they are trained: parameterized circuits, gradients, data encoding and barren plateaus.
Quantum neural network architectures and how they are trained: parameterized circuits, gradients, data encoding and barren plateaus.
Quantum decision theory models choices with quantum probability to capture biases and paradoxes. Its origins, uses and criticisms.
Quantum cognitive models apply quantum probability to memory, judgment and decision-making. What they explain and how they are tested.
A survey of quantum machine learning: data encoding, feature maps, quantum neural networks, claimed speedups and open challenges.
An honest picture of quantum artificial intelligence: what quantum machine learning can do today, the hardware limits and open problems.
Randomness expansion uses a short random seed and entangled devices to certify a longer string of true random bits. How and why it works.
The main quantum cloud platforms compared, including IBM Quantum, Amazon Braket and Azure Quantum: what they offer, costs and limitations.
Quantum reinforcement learning combines quantum computing with reward-driven learning. Claimed speedups, uses and current limitations.
Quantum stochastic modeling combines quantum mechanics with random processes to describe open, noisy systems. Methods and applications.
How quantum computing might support autonomous systems through faster optimization, machine learning and navigation, and the open questions.
Quantum data fusion combines information from several noisy sources. How quantum methods might help and how they compare with classical fusion.
Quantum models of cognition use the mathematics of quantum probability to describe human judgments. Key ideas, evidence and criticism.