The Experts below are selected from a list of 10227 Experts worldwide ranked by ideXlab platform
Chrystopher L. Nehaniv - One of the best experts on this subject based on the ideXlab platform.
-
Sensorimotor experience and its metrics: Informational geometry and the temporal horizon
2005 IEEE Congress on Evolutionary Computation, 2005Co-Authors: Chrystopher L. NehanivAbstract:We introduce metrics on sensorimotor experience at various temporal scales based on Information-Theory. Sensorimotor variables through which the experience of an agent flows are modeled as Information sources in the sense of Shannon Information Theory. Information distance between the constellation of an embodied agent's sensorimotor variables at different moments in time can be taken variable-by-variable or between entire sets of such variables to yield two classes of metrics on sensorimotor experience: the temporal experiential Information distance and the Hausdorff metric on experience. Unlike mutual Information, these measures each satisfy the metric axioms and thus induce a geometry on the space of experiences with the same temporal scope. Continuity of maps between experiential spaces as well as robotic applications and extensions are discussed
-
Meaningful Information, Sensor Evolution, and the Temporal Horizon of Embodied Organisms
Artificial Life, 2002Co-Authors: Chrystopher L. Nehaniv, Daniel Polani, Kerstin DautenhahnAbstract:We survey and outline how an agent-centered, Information-theoretic approach to meaningful Information extending classical Shannon Information Theory by means of utility measures relevant for the goals of particular agents can be applied to sensor evolution for real and constructed organisms. Furthermore, we discuss the relationship of this approach to the programme of freeing artificial life and robotic systems from reactivity, by describing useful types of Information with broader temporal horizon, for signaling, communication, affective grounding, two-process learning, individual learning, imitation and social learning, and episodic experiential Information (memories, narrative, and culturally transmitted Information).
David Ellerman - One of the best experts on this subject based on the ideXlab platform.
-
logical entropy introduction to classical and quantum logical Information Theory
Social Science Research Network, 2018Co-Authors: David EllermanAbstract:Logical Information Theory is the quantitative version of the logic of partitions just as logical probability Theory is the quantitative version of the dual Boolean logic of subsets. The resulting notion of Information is about distinctions, differences and distinguishability and is formalized using the distinctions (“dits”) of a partition (a pair of points distinguished by the partition). All the definitions of simple, joint, conditional and mutual entropy of Shannon Information Theory are derived by a uniform transformation from the corresponding definitions at the logical level. The purpose of this paper is to give the direct generalization to quantum logical Information Theory that similarly focuses on the pairs of eigenstates distinguished by an observable, i.e., qudits of an observable. The fundamental theorem for quantum logical entropy and measurement establishes a direct quantitative connection between the increase in quantum logical entropy due to a projective measurement and the eigenstates (cohered together in the pure superposition state being measured) that are distinguished by the measurement (decohered in the post-measurement mixed state). Both the classical and quantum versions of logical entropy have simple interpretations as “two-draw” probabilities for distinctions. The conclusion is that quantum logical entropy is the simple and natural notion of Information for quantum Information Theory focusing on the distinguishing of quantum states.
Andrey V Savkin - One of the best experts on this subject based on the ideXlab platform.
-
an analogue of Shannon Information Theory for detection and stabilization via noisy discrete communication channels
Siam Journal on Control and Optimization, 2007Co-Authors: Alexey S Matveev, Andrey V SavkinAbstract:The paper addresses both detection and stabilization problems involving communication errors and capacity constraints. Discrete-time partially observed linear systems are studied. Unlike the classic Theory, the sensor signals are transmitted to the estimator/controller over a noisy digital communication link modeled as a stochastic stationary discrete memoryless channel. It is shown that for noise-free plants, the Shannon capacity of the channel constitutes the border separating the cases where stabilization and reliable detection (asymptotic state estimation) with arbitrarily large probability are and are not possible, respectively.
-
an analogue of Shannon Information Theory for networked control systems state estimation via a noisy discrete channel
Conference on Decision and Control, 2004Co-Authors: Alexey S Matveev, Andrey V SavkinAbstract:The paper addresses a state estimation problem involving bit-rate communication capacity constraints. A discrete-time partially observed linear system is studied. Unlike the classic Theory, the sensor signals are transmitted to the estimator over a noisy digital communication channel. A recursive coder-decoder state estimation scheme is proposed and investigated. It is shown that the classic Shannon's noisy channel capacity constitutes the border separating the cases where the reliable state estimation is and, respectively, is not possible with arbitrarily high probability.
K R W Jones - One of the best experts on this subject based on the ideXlab platform.
-
fundamental limits upon the measurement of state vectors
Physical Review A, 1994Co-Authors: K R W JonesAbstract:Using the Shannon Information Theory and the Bayesian methodology for inverting quantum data [K. R. W. Jones, Ann. Phys. (N.Y.) 207, 140 (1991)] we prove a fundamental bound upon the measurability of finite-dimensional quantum states. To do so we imagine a thought experiment for the quantum communication of a pure state , known to one experimenter, to his colleague via the transmission of N identical copies of it in the limit of zero temperature. Initial Information available to the second experimenter is merely that of the allowed manifold of superpositions upon which the chosen may lie. Her efforts to determine it, in an optimal way, subject to the fundamental constraints imposed by quantum noise, define a statistical uncertainty principle. This limits the accuracy with which can be measured according to the number N of transmitted copies. The general result is illustrated in the physically realizable case of polarized photons.
Nicolas J Cerf - One of the best experts on this subject based on the ideXlab platform.
-
entropy power uncertainty relations towards a tight inequality for all gaussian pure states
Journal of Physics A, 2017Co-Authors: Anaelle Hertz, Michael G Jabbour, Nicolas J CerfAbstract:We show that a proper expression of the uncertainty relation for a pair of canonically-conjugate continuous variables relies on entropy power, a standard notion in Shannon Information Theory for real-valued signals. The resulting entropy-power uncertainty relation is equivalent to the entropic formulation of the uncertainty relation due to Bialynicki-Birula and Mycielski, but can be further extended to rotated variables. Hence, based on a reasonable assumption, we give a partial proof of a tighter form of the entropy-power uncertainty relation taking correlations into account and provide extensive numerical evidence of its validity. Interestingly, it implies the generalized (rotation-invariant) Schrodinger–Robertson uncertainty relation exactly as the original entropy-power uncertainty relation implies Heisenberg relation. It is saturated for all Gaussian pure states, in contrast with hitherto known entropic formulations of the uncertainty principle.
-
Information Theory of quantum entanglement and measurement
Physica D: Nonlinear Phenomena, 1998Co-Authors: Nicolas J Cerf, Chris AdamiAbstract:Abstract We present a quantum Information Theory that allows for a consistent description of entanglement. It parallels classical (Shannon) Information Theory but is based entirely on density matrices rather than probability distributions for the description of quantum ensembles. We find that quantum (von Neumann) conditional entropies can be negative for entangled systems, which leads to a violation of entropic Bell inequalities. Quantum inseparability can be related, in this Theory, to the appearance of “unclassical” eigenvalues in the spectrum of a conditional “amplitude” matrix that underlies the quantum conditional entropy. Such a unified Information-theoretic description of classical correlation and quantum entanglement clarifies the link between them: the latter can be viewed as “super-correlation” which can induce classical correlation when considering a tripartite or larger system. Furthermore, the characterization of entanglment with negative conditional entropies paves the way to a natural Information-theoretic description of the measurement process. This model, while unitary and causal, implies the well-known probabilistic results of conventional quantum mechanics. It also results in a simple interpretation of the Levitin-Kholevo theorem limiting the accessible Information in a quantum measurement.
-
quantum Information Theory of entanglement and measurement
arXiv: Quantum Physics, 1996Co-Authors: Nicolas J Cerf, Chris AdamiAbstract:We present a quantum Information Theory that allows for a consistent description of entanglement. It parallels classical (Shannon) Information Theory but is based entirely on density matrices (rather than probability distributions) for the description of quantum ensembles. We find that quantum conditional entropies can be negative for entangled systems, which leads to a violation of well-known bounds in Shannon Information Theory. Such a unified Information-theoretic description of classical correlation and quantum entanglement clarifies the link between them: the latter can be viewed as ``super-correlation'' which can induce classical correlation when considering a tripartite or larger system. Furthermore, negative entropy and the associated clarification of entanglement paves the way to a natural Information-theoretic description of the measurement process. This model, while unitary and causal, implies the well-known probabilistic results of conventional quantum mechanics. It also results in a simple interpretation of the Kholevo theorem limiting the accessible Information in a quantum measurement.