Quantum learning for neural associative memories

Kathleen E. Hamilton, Jonathan Schrock, Neena Imam +1 more

Tariq Mahmood, Rehan Ahmad Khan Sherwani

Abstract Perceptual memory is important for human cognition and learning because it plays an important role in forming consciousness, memories, learning, and stimulus awareness. Perceptual memory assists in the recognition of items or faces, as well as in the sorting, differentiating, and combining of new information with context and emotions. Perceptual-associative memory encodes information structurally, semantically, and phonetically. It interacts with the conscious artifact's medium-term memory (MTM), long-term memory (LTM), workspace, and emotion modules to construct meanings and connections to chosen sensory information. This research developed a quantum cognitive model of perceptual associative memory to replicate human-like perceptual cognitions in conscious artifacts. Moreover, for the quantum neural correlates of consciousness, this research has also simulated the circuit of the quantum neural network for non-linear learning of an XOR gate using the qiskit library.

Naoki Masuyama, Chu Kiong Loo, Manjeevan Seera +1 more

Quantum-inspired computing is an emerging research area, which has significantly improved the capabilities of conventional algorithms. In general, quantum-inspired hopfield associative memory (QHAM) has demonstrated quantum information processing in neural structures. This has resulted in an exponential increase in storage capacity while explaining the extensive memory, and it has the potential to illustrate the dynamics of neurons in the human brain when viewed from quantum mechanics perspective although the application of QHAM is limited as an autoassociation. We introduce a quantum-inspired multidirectional associative memory (QMAM) with a one-shot learning model, and QMAM with a self-convergent iterative learning model (IQMAM) based on QHAM in this paper. The self-convergent iterative learning enables the network to progressively develop a resonance state, from inputs to outputs. The simulation experiments demonstrate the advantages of QMAM and IQMAM, especially the stability to recall reliability.

Mitja Peruš

Moolchand Sharma, Nebojša Bačanin, Tarik Ahmed Rashid

Yoshihiro Osakabe, Hisanao Akima, Masao Sakuraba +2 more

There is increasing interest in quantum computing, because of its enormous computing potential. A small number of powerful quantum algorithms have been proposed to date; however, the development of new quantum algorithms for practical use remains essential. Parallel computing with a neural network has successfully realized certain unique functions such as learning and recognition; therefore, the introduction of certain neural computing techniques into quantum computing to enlarge the quantum computing application field is worthwhile. In this paper, a novel quantum associative memory (QuAM) is proposed, which is achieved with a quantum neural network by employing adiabatic Hamiltonian evolution. The memorization and retrieval procedures are inspired by the concept of associative memory realized with an artificial neural network. To study the detailed dynamics of our QuAM, we examine two types of Hamiltonians for pattern memorization. The first is a Hamiltonian having diagonal elements, which is known as an Ising Hamiltonian and which is similar to the cost function of a Hopfield network. The second is a Hamiltonian having non-diagonal elements, which is known as a neuro-inspired Hamiltonian and which is based on interactions between qubits. Numerical simulations indicate that the proposed methods for pattern memorization and retrieval work well with both types of Hamiltonians. Further, both Hamiltonians yield almost identical performance, although their retrieval properties differ. The QuAM exhibits new and unique features, such as a large memory capacity, which differs from a conventional neural associative memory.