Goto

Collaborating Authors

Learning Continuous-Time Bayesian Networks in Relational Domains: A Non-Parametric Approach

AAAI Conferences

Many real world applications in medicine, biology, communication networks, web mining, and economics, among others, involve modeling and learning structured stochastic processes that evolve over continuous time. Existing approaches, however, have focused on propositional domains only. Without extensive feature engineering, it is difficult-if not impossible-to apply them within relational domains where we may have varying number of objects and relations among them. We therefore develop the first relational representation called Relational Continuous-Time Bayesian Networks (RCTBNs) that can address this challenge. It features a nonparametric learning method that allows for efficiently learning the complex dependencies and their strengths simultaneously from sequence data. Our experimental results demonstrate that RCTBNs can learn as effectively as state-of-the-art approaches for propositional tasks while modeling relational tasks faithfully.


A Logic-Based Methodology for the Formalization of Shikake Principles and Examples

AAAI Conferences

Shikake is a design approach that proposes solving problems by inducing spontaneous behavior, rather than by relying on the use of extensive resources or expertise. This paper contributes to the study of Shikake principles and examples by describing a methodology for their formalization in the declarative, logic-based language of Answer Set Prolog (ASP). Modeling qualitative theories and principles such as Shikake in the precise language of ASP can play a significant role in indicating possible areas for their future refinement and improvement, as shown here. Our formalization is used in creating a system, SHASP, that can automatically determine if a design is a Shikake or not, as illustrated by two examples and one counterexample.


He's wanting for Bayesian time-series examples

#artificialintelligence

Coming from the standard side, begun to use Bayes, speedily limiting it to designs with significantly less variables, notwithstanding the entice. Am not in lecturers but have for a lot of several years investigated style and design processes of complex objects these types of as engineering complex process vegetation. These processes have a guide-time from 12 to eighteen months. Purpose was to check on progress of variables that could suggest derailment of process. Felt cozy in applying posterior to update new prior, a 7 days afterwards, especially two months into the process.


#DigitalBusiness and #AI should use Hegelian Logic to find very different and valuable customer insights – Paradigm Interactions

#artificialintelligence

There is a continuous drive for human to be more like machines, but the problem is they are not. No matter how well a business or product message is crafted everyone that hears it, hears it differently. They hear it according to their experiences, their knowledge and this is why mass market media exists in the hope of shooting wide and attracting some part of peoples attentions and thinking patterns.


#DigitalBusiness and #AI should use Hegelian Logic to find very different and valuable customer insights – Paradigm Interactions

#artificialintelligence

There is a continuous drive for human to be more like machines, but the problem is they are not. No matter how well a business or product message is crafted everyone that hears it, hears it differently. They hear it according to their experiences, their knowledge and this is why mass market media exists in the hope of shooting wide and attracting some part of peoples attentions and thinking patterns. In this generation AI will have a huge impact, however machines work in an absolute form of Socratic Logic which is not how humans think. Science has a huge responsibility here, as it has pushed an absolute notion of things and people.