Can Machine Learning Turn Big Data into No Big Deal?


Is machine learning (ML) or artificial intelligence (AI) the key? Companies have worked on many ways to offer plug-and-play sensor packages to collect information, with multiple options to send it where ever it needs to go. To reap the benefits of a higher-performing data network such as IIoT, ML, or Big Data, an interdisciplinary communication network is essential. "OT professionals are focused on keeping manufacturing, plant, and physical equipment in operation for extended periods of time, while IT professionals focus on keeping data flowing and accessible to all facets of an organization," says Dariol.

Report 84 39 W Stanford KSL 4111111 111 stlentlfic

Classics (Collection 2)

Reprinted, with permission, from the Proceedings of the IEEE Workshop on Principles of Knowledge-Based Systems, December 1984. John McC3rmott and Allen Newell are at the Carnegie-Mellon University Computer Science Department. Most of this work was done while Paul Rosenbloom and John Laird were also at CMU CSD. Paul Rosenbloom is now at the Stanford University Departments of Computer Science and Psychology. John Laird is now at the Xerox Palo Alto Research Center.

Report 79-18.pdf

Classics (Collection 2)

INTRODUCTION Since the early 1970's, researchers on computei-- based medical reasoning have begun to recognize the potential benefits of applying symbolic reasoning techniques in clinical domains This report discusses the strengths of this form of knowledge representation and shows how production rules can be applied in two somewhat different clinical applications. We begin by presenting the reasons that symbolic processing has been utilized for medical decision making. A brief discussion of the MYCIN program and a more detailed discussion of the VM program are included to demonstrate the use of the symbolic processing techniques. The design criteria for the two programs are compared. Differences in design criteria, plus experience with the MYCIN program, led to the extensions to the methodology described in the final section. 2 THE RATIONALE FOR USING SYMBOLIC PROCESSING TECHNIQUES There is increasing evidence that computer-based diagnosis and therapy programs will be accepted - Several sets of design requirements have been suggested [4, 5].

dik Stanford KSL

Classics (Collection 2)

Although the system's emphasis is on the selection of appropriate therapy for critically ill patients, it also necessarily assists with certain aspects of infectious disease diagnosis. This paper provides a brief overview of the program, describing in particular its scheme for the representation of clinical knowledge and the ways in which this representation facilitates both the generation of advice and the explanation of decisicns. The encoding of knowledge in production rules, which are analyzed for advice generation by a goal-oriented rule interpreter, also permits a!limple but powerful approach to natural language understanding. Despite its limitations, this approach provides an effective explanation capability without addressing many of the complex problems encountered in computational linguistics. The flow of information betveen a user and the MYCIN system is compared to that which occurs when'a physician seeks the advice of a humen infectioe:; di:;ease conrultant. 1. INTRODUCTION As medical knowledge has expanded in recent decades, it has become evident that the individual practitioner can no longer hope to acquire enough expertise to manage adequately the full range of clinical problems that will be encountered in his practice.


Classics (Collection 2)

R l is a program that configures VAX -11/780 computersystems. Given a customer's order, it determines R1 is implemented as a production system. Consequently, little search is required in order for it (a configure a computer system. R1' is a rulc-based system that has much in common with other domain-specific "The development of R1 was supported by Digital Equipment Corporation. ARPA Or er No. 3597, and monitored by MASSBUS are tradmarks of Digital Equipment Corporation.