Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Michael G. Dyer is active.

Publication


Featured researches published by Michael G. Dyer.


Connection Science | 1989

High-level Inferencing in a Connectionist Network

Trent E. Lange; Michael G. Dyer

Connectionist models have had problems representing and applying general knowledge rules that specifically require variables. This variable binding problem has barred them from performing the high-...


Cognitive Science | 1991

Natural Language Processing With Modular Pdp Networks and Distributed Lexicon

Risto Miikkulainen; Michael G. Dyer

An approach to connectionist natural language processing is proposed, which is based on hierarchically organized modular Parallel Distributed Processing (PDP) networks and a central lexicon of distributed input/output representations. The modules communicate using these representations, which are global and publicly available in the system. The representations are developed automatically by all networks while they are learning their processing tasks. The resulting representations re ect the regularities in the subtasks, which facilitates robust processing in the face of noise and damage, supports improved generalization, and provides expectations about possible contexts. The lexicon can be extended by cloning new instances of the items, that is, by generating a number of items with known processing properties and distinct identities. This technique combinatorially increases the processing power of the system. The recurrent FGREP module, together with a central lexicon, is used as a basic building block in modeling higher level natural language tasks. A single module is used to form case-role representations of sentences from word-by-word sequential natural language input. A hierarchical organization of four recurrent FGREP modules (the DISPAR system) is trained to produce fully expanded paraphrases of script-based stories, where unmentioned events and role llers are inferred.


Cognition & Emotion | 1987

Emotions and their computations: Three computer models

Michael G. Dyer

Abstract Three computational models: a narrative reader (BORIS), an editorial reader (OpEd), and a stream of thought generator (DAYDREAMER), are presented and discussed, with specific focus on the emotion-related processing and representational elements of each. These models exhibit comprehension and/or generation of emotional behaviour through the interaction of cognitive processes (memory retrieval, planning, and reasoning) over intentional constructs (goals and beliefs).


Cognitive Science | 1983

The Role of Affect in Narratives

Michael G. Dyer

Affect states and reactions commonly occur in narratives. This paper discusses the importance of affect knowledge and processing in the context of BORIS, a computer program which reads and answers questions about narratives involving multiple sources of knowledge. There are several reasons why affects are important in a process model of narrative comprehension: For one thing, affects describe goal situations and signal the occurrence of expectation failures. Affective reactions also serve as an indication of the status of interpersonal relationships. Finally, affects influence the kinds of thematic structures which become instantiated in episodic memory.


Artificial Intelligence | 1983

BORIS -- An Experiment in In-Depth Understanding of Narratives.

Wendy G. Lehnert; Michael G. Dyer; Peter N. Johnson; C.J. Yang; Steve Harley

Abstract boris is an experimental story understanding and question answering system which deals with the specification and interaction of many sources of knowledge. Unlike skimmers, which simply extract the “gist” of a story in a top-down manner and ignore everything else, boris attempts to understand everything that it reads to as great a depth as possible. This report focuses on how the boris program handles a complex story involving a divorce.


Artificial Intelligence in Engineering | 1986

EDISON: An engineering design invention system operating naively

Michael G. Dyer; Margot Flowers; Jack Hodges

The goal of the EDISON project is to design a program capable of creating novel mechani-cal devices, by using knowledge of naive physical relationships, qualitative reasoning, plan-ning, and discovery/invention heuristics applied to abstract devices organized and indexed in an episodic memory. The EDISON program operates in two modes: brainstorming mode and problem-solving mode. In problem-solving mode, a goal specification is given as input and EDISON attempts to achieve the goal through plan selection and sub-goal satisfaction. A goal specification can be to alter or improve a device. Devices are represented symboli-cally, and are reasoned upon by EDISON without performing numerical computations. In brainstorming mode, EDISON starts with a device recalled from memory, and attempts to create novel devices through processes of mutation, generalization and analogical reason-ing. The devices EDISON manipulates consist of simple, everyday mechanisms, such as mousetraps, nail clippers, can openers and doors. A goal of the EDISON project is to gain computational insight into the processes of naive physical reasoning [Hayes 78] and inven-tion [Lenat 76] which people exhibit. To do so, we must address a number of issues, includ-ing: (a) how devices are represented and manipulated without detailed mathematical rea-soning, (b) how devices are organized, indexed, and retrieved from a personal, episodic memory of devices and experiences of device use, (c) how new devices are discovered or in-vented during problem solving and/or brainstorming, and (d) how the resulting inventions are assessed for their novelty and/or ingenuity.


Molecular Microbiology | 1996

Expression and regulation of the rnc and pdxJ operons of Escherichia coli

James Matsunaga; Michael G. Dyer; Elizabeth L. Simons; Robert W. Simons

Escherichia coli rnc–era–recO operon (rnc operon) expression is negatively autoregulated at the level of message stability by ribonuclease III (RNase III), which is encoded by the rnc gene. RNase III, a double‐stranded RNA‐specific endoribonuclease involved in rRNA and mRNA processing and degradation, cleaves a stem‐loop structure in the 5′ untranslated leader, initiating rapid decay of the rnc operon mRNA. Here, we examine rnc operon expression and regulation in greater detail. Northern, primer extension, and lacZ fusion analyses show that a single promoter (rncP ) specifies two principal mRNAs: the 1.9 kb rnc–era transcript and the less‐abundant 3.7 kb RNA encoding rnc–era–recO and the downstream pdxJ and acpS genes. A 1.3 kb pdxJ–acpS RNA is transcribed from a promoter (pdxP ) located within recO. About 70% of pdxJ transcription depends on transcription from rncP. Both promoters were characterized genetically. RNase III reduces 1.9 kb and 3.7 kb transcript levels and stability, and corresponding effects are seen with genetic fusions. These detailed studies enabled us to show that the first 378 nucleotides of the rnc transcript comprise a portable RNA stability element (rncO) that contains all of the cis‐acting elements required for RNase III‐initiated decay of the rnc mRNA as well as the heterologous lacZ transcript. Moreover, mutations in rncO that block RNase III cleavage also block control, showing that RNase III initiates mRNA decay by cleaving at a single site.


Advances in psychology | 1982

Question Answering for Narrative Memory

Michael G. Dyer; Wendy G. Lehnert

BORIS represents the first system to integrate the knowledge-based inference techniques of scripts. plans, goals, and themes. within a single narrative understanding program. This paper discusses techniques used by BORIS for memory representation and memory retrieval. Emphasis is placed on human question answering abilities. and the heuristics needed to simulate these phenomena. An example narrative processed by BORIS is discussed in detail and used to illustrate design features.


Journal of Experimental and Theoretical Artificial Intelligence | 1990

Distributed symbol formation and processing in connectionist networks

Michael G. Dyer

Abstract Distributed connectionist (DC) systems offer a set of processing features which are distinct from those provided by traditional symbol processing (SP) systems. In general, the features of DC systems are derived from the nature of their distributed representations. Such representations have a microsemantics -i.e. symbols with similar internal representations tend to have similar processing effects. In contrast, the symbols in SP systems have no intrinsic microsemantics of their own; e.g. SP symbols are formed by concatenating ASCII codes that are static, human engineered and arbitrary. Such symbols possess only a macrosemantics - i.e. symbols are placed into structured relationships with other symbols, via pointers, and bindings are propagated via variables. The fact that DC and SP systems each provide a distinct set of useful features serves as a strong research motivation for seeking a synthesis. What is needed for such a synthesis is a method by which symbols can dynamically form their own micr...


Connection Science | 1990

Learning Distributed Representations of Conceptual Knowledge and their Application to Script-based Story Processing

Geunbae Lee; Margot Flowers; Michael G. Dyer

We propose a new method for developing distributed connectionist representations in order to serve as an adequate foundation for constructing and manipulating conceptual knowledge. In our approach, distributed representations of semantic relations (i.e. propositions) are formed by recirculating the hidden layer in two auto-associative recurrent PDP (parallel distributed processing) networks, and our experiments show that the resulting distributed semantic representations (DSRs) have many desirable properties such as automaticity, portability, structure-encoding ability and similarity-based distributed representations. We have constructed a symbolic/connectionist hybrid script-based story processing system dynasty (DYNAmic STory understanding sYstem) which incorporates DSR learning and 6 script related processing modules. Each module communicates through a global dictionary, where DSRs are stored, dynasty is able to (1) learn similarity-based distributed representations of concepts and events in everyday scriptal experiences, (2) perform script-based causal chain completion inferences according to the acquired sequential knowledge, and (3) perform script role association and retrieval during script application.

Collaboration


Dive into the Michael G. Dyer's collaboration.

Top Co-Authors

Avatar

Margot Flowers

University of California

View shared research outputs
Top Co-Authors

Avatar

Anand V. Panangadan

University of Southern California

View shared research outputs
Top Co-Authors

Avatar

Gerald Chao

University of California

View shared research outputs
Top Co-Authors

Avatar

Risto Miikkulainen

University of Texas at Austin

View shared research outputs
Top Co-Authors

Avatar

Alex Quilici

University of California

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Jack Hodges

University of California

View shared research outputs
Top Co-Authors

Avatar

Trent E. Lange

University of California

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge