We implement a mechanism - originally proposed as a model for the large memory storage capacity of black holes - in quantum neural networks and show that an exponentially increased capacity of pattern storage and recognition is achieved in certain critically excited states, without involvement of synaptic plasticity. We consider a simple network of N interconnected quantum neurons with weak excitatory synaptic connections. We show that for frozen synaptic weights there exist the critical states of enhanced memory storage capacity. These states are achieved thanks to the high excitation levels of some of the neurons, which - despite of feeble synaptic connections - dramatically lower the response threshold of the remaining weaker-excited neurons. As a results, the latter neurons acquire a capacity to store an exponentially large number of patterns within a narrow energy gap. The stored patterns can be recognized and retrieved with perfect response under the influence of arbitrarily soft input stimuli. In sharp contrast, under the same stimuli the recall is absent in the ground-state of the system. The lesson is that the state with the highest micro-state entropy and memory storage capacity is not necessarily a local minimum of energy, but rather an excited critical state. The considered phenomenon has a smooth classical limit and can serve for achieving an enhanced memory storage capacity in classical brain networks.
We implement a mechanism - originally proposed as a model for the large memory storage capacity of black holes - in quantum neural networks and show that an exponentially increased capacity of pattern storage and recognition is achieved in certain critically excited states, without involvement of synaptic plasticity. We consider a simple network of N interconnected quantum neurons with weak excitatory synaptic connections. We show that for frozen synaptic weights there exist the critical states of enhanced memory storage capacity. These states are achieved thanks to the high excitation levels of some of the neurons, which - despite of feeble synaptic connections - dramatically lower the response threshold of the remaining weaker-excited neurons. As a results, the latter neurons acquire a capacity to store an exponentially large number of patterns within a narrow energy gap. The stored patterns can be recognized and retrieved with perfect response under the influence of arbitrarily soft input stimuli. In sharp contrast, under the same stimuli the recall is absent in the ground-state of the system. The lesson is that the state with the highest micro-state entropy and memory storage capacity is not necessarily a local minimum of energy, but rather an excited critical state. The considered phenomenon has a smooth classical limit and can serve for achieving an enhanced memory storage capacity in classical brain networks.
Motivated by the potential similarities between the underlying mechanisms of the enhanced memory storage capacity in black holes and in brain networks, we construct an artificial quantum neural network based on gravity-like synaptic connections and a symmetry structure that allows to describe the network in terms of geometry of a d-dimensional space. We show that the network possesses a critical state in which the gapless neurons emerge that appear to inhabit a (d-1)-dimensional surface, with their number given by the surface area. In the excitations of these neurons, the network can store and retrieve an exponentially large number of patterns within an arbitrarily narrow energy gap. The corresponding micro-state entropy of the brain network exhibits an area law. The neural network can be described in terms of a quantum field, via identifying the different neurons with the different momentum modes of the field, while identifying the synaptic connections among the neurons with the interactions among the corresponding momentum modes. Such a mapping allows to attribute a well-defined sense of geometry to an intrinsically non-local system, such as the neural network, and vice versa, it allows to represent the quantum field model as a neural network.
Abstract Motivated by the potential similarities between the underlying mechanisms of the enhanced memory storage capacity in black holes and in brain networks, we construct an artificial quantum neural network based on gravity‐like synaptic connections and a symmetry structure that allows to describe the network in terms of geometry of a d‐dimensional space. We show that the network possesses a critical state in which the gapless neurons emerge that appear to inhabit a ‐dimensional surface, with their number given by the surface area. In the excitations of these neurons, the network can store and retrieve an exponentially large number of patterns within an arbitrarily narrow energy gap. The corresponding micro‐state entropy of the brain network exhibits an area law. The neural network can be described in terms of a quantum field, via identifying the different neurons with the different momentum modes of the field, while identifying the synaptic connections among the neurons with the interactions among the corresponding momentum modes. Such a mapping allows to attribute a well‐defined sense of geometry to an intrinsically non‐local system, such as the neural network, and vice versa, it allows to represent the quantum field model as a neural network.
We discuss a class of quantum theories which exhibit a sharply increased memory storage capacity due to emergent gapless degrees of freedom. Their realization, both theoretical and experimental, is of great interest. On the one hand, such systems are motivated from a quantum information point of view. On the other hand, they can provide a framework for simulating systems with enhanced capacity of pattern storage, such as black holes and neural networks. In this paper, we develop an analytic method that enables us to find critical states with increased storage capabilities in a generic system of cold bosons with weak attractive interactions. The enhancement of memory capacity arises when the occupation number N of certain modes reaches a critical level. Such modes, via negative energy couplings, assist others in becoming effectively gapless. This leads to degenerate microstates labeled by the occupation numbers of the nearly-gapless modes. In the limit of large N , they become exactly gapless and their decoherence time diverges. In this way, a system becomes an ideal storer of quantum information. We demonstrate our method on a prototype model of N attractive cold bosons contained in a one-dimensional box with Dirichlet boundary conditions. Although we limit ourselves to a truncated system, we observe a rich structure of quantum phases with a critical point of enhanced memory capacity.
We review our models of quantum associative memories that represent the “quantization” of fully coupled neural networks like the Hopfield model. The idea is to replace the classical irreversible attractor dynamics driven by an Ising model with pattern-dependent weights by the reversible rotation of an input quantum state onto an output quantum state consisting of a linear superposition with probability amplitudes peaked on the stored pattern closest to the input in Hamming distance, resulting in a high probability of measuring a memory pattern very similar to the input. The unitary operator implementing this transformation can be formulated as a sequence of one-qubit and two-qubit elementary quantum gates and is thus the exponential of an ordered quantum Ising model with sequential operations and with pattern-dependent interactions, exactly as in the classical case. Probabilistic quantum memories, that make use of postselection of the measurement result of control qubits, overcome the famed linear storage limitation of their classical counterparts because they permit to completely eliminate crosstalk and spurious memories. The number of control qubits plays the role of an inverse fictitious temperature. The accuracy of pattern retrieval can be tuned by lowering the fictitious temperature under a critical value for quantum content association while the complexity of the retrieval algorithm remains polynomial for any number of patterns polynomial in the number of qubits. These models thus solve the capacity shortage problem of classical associative memories, providing a polynomial improvement in capacity. The price to pay is the probabilistic nature of information retrieval.
Quantum neural networks form one pillar of the emergent field of quantum machine learning. Here quantum generalizations of classical networks realizing associative memories---capable of retrieving patterns, or memories, from corrupted initial states---have been proposed. It is a challenging open problem to analyze quantum associative memories with an extensive number of patterns and to determine the maximal number of patterns the quantum networks can reliably store, i.e., their storage capacity. In this work, we propose and explore a general method for evaluating the maximal storage capacity of quantum neural network models. By generalizing what is known as Gardner's approach in the classical realm, we exploit the theory of classical spin glasses for deriving the optimal storage capacity of quantum networks with quenched pattern variables. As an example, we apply our method to an open-system quantum associative memory formed of interacting spin-1/2 particles realizing coupled artificial neurons. The system undergoes a Markovian time evolution resulting from a dissipative retrieval dynamics that competes with a coherent quantum dynamics. We map out the nonequilibrium phase diagram and study the effect of temperature and Hamiltonian dynamics on the storage capacity. Our method opens an avenue for a systematic characterization of the storage capacity of quantum associative memories.
An explicit microscopic realization of the phenomenon of holography is provided by a class of simple quantum theories of a bosonic field inhabiting a d-dimensional space and experiencing a momentum dependent attractive interaction. An exact mode counting reveals a family of holographic states. In each a set of gapless modes emerges with their number equal to the area of a (d-1)-dimensional sphere. These modes store an exponentially large number of patterns within a microscopic energy gap. The resulting micro-state entropy obeys the area-law reminiscent of a black hole entropy. We study the time-evolution of the stored patterns and observe the following phenomenon: Among the degenerate micro-states the ones with heavier loaded memories survive longer than those that store emptier patterns. Thus, a state gets stabilized by the burden of its own memory. From time to time the information pattern gets off-loaded from one holographic state into another but cannot escape the system. During this process the pattern becomes highly entangled and scrambled. We suggest that this phenomenon is universal in systems with enhanced memory storage capacity, such as black holes or critical neural networks. This universality sheds an interesting light on the puzzle of why, despite the evaporation, is a black hole forced to maintain information internally for a very long time.