Collaborating Authors

Enterprise Information Security


Though Information security falls under everyone's responsibility, IT function plays a crucial role in preventing Information security breaches by enhancing/implementing controls with apt technology tools and infrastructure. It is always advisable to go with Org wide third party security assessments through ISO/IEC 27001 standard to get a 360 degree view on current controls and to identify gaps that may adversely impact on organization's security controls.

A Generalized Information Formula as the Bridge between Shannon and Popper Artificial Intelligence

A generalized information formula related to logical probability and fuzzy set is deduced from the classical information formula. The new information measure accords with to Popper's criterion for knowledge evolution very much. In comparison with square error criterion, the information criterion does not only reflect error of a proposition, but also reflects the particularity of the event described by the proposition. It gives a proposition with less logical probability higher evaluation. The paper introduces how to select a prediction or sentence from many for forecasts and language translations according to the generalized information criterion. It also introduces the rate fidelity theory, which comes from the improvement of the rate distortion theory in the classical information theory by replacing distortion (i.e. average error) criterion with the generalized mutual information criterion, for data compression and communication efficiency. Some interesting conclusions are obtained from the rate-fidelity function in relation to image communication. It also discusses how to improve Popper's theory.


AAAI Conferences

I have been working in the field of information integration since 1990, when I established the SIMS (Single Interface to Multiple Sources) research project at the University of Southern California's Information Sciences Institute. Since that time, the SIMS project has expanded into a group of several coordinated research efforts involving approximately 15 research staff and students, including some of the top researchers in the field today.

Unification of Information Maximization and Minimization

Neural Information Processing Systems

In the present paper, we propose a method to unify information maximization and minimization in hidden units. The information maximization and minimization are performed on two different levels: collectiveand individual level. Thus, two kinds of information: collective and individual information are defined. By maximizing collective information and by minimizing individual information, simple networks can be generated in terms of the number of connections andthe number of hidden units. Obtained networks are expected to give better generalization and improved interpretation of internal representations.

Generalizing Information to the Evolution of Rational Belief Machine Learning

Information theory provides a mathematical foundation to measure uncertainty in belief. Belief is represented by a probability distribution that captures our understanding of an outcome's plausibility. Information measures based on Shannon's concept of entropy include realization information, Kullback-Leibler divergence, Lindley's information in experiment, cross entropy, and mutual information. We derive a general theory of information from first principles that accounts for evolving belief and recovers all of these measures. Rather than simply gauging uncertainty, information is understood in this theory to measure change in belief. We may then regard entropy as the information we expect to gain upon realization of a discrete latent random variable. This theory of information is compatible with the Bayesian paradigm in which rational belief is updated as evidence becomes available. Furthermore, this theory admits novel measures of information with well-defined properties, which we explore in both analysis and experiment. This view of information illuminates the study of machine learning by allowing us to quantify information captured by a predictive model and distinguish it from residual information contained in training data. We gain related insights regarding feature selection, anomaly detection, and novel Bayesian approaches.