Papers by Aregahegn Negatu
Cognitively Inspired Anticipatory Adaptation and Associated Learning Mechanisms for Autonomous Agents
Lecture Notes in Computer Science
This paper describes the integration of several cognitively inspired anticipation and anticipator... more This paper describes the integration of several cognitively inspired anticipation and anticipatory learning mechanisms in an autonomous agent architecture, the Learning Intelligent Distribution Agent (LIDA) system. We provide computational mechanisms and experimental simulations for variants of payoff, state, and sensorial anticipatory mechanisms. The payoff anticipatory mechanism in LIDA is implicitly realized by the action selection dynamics of LIDA's decision making component, and is enhanced by importance ...
Here we describe mechanisms for a half-dozen or so different types of learning to be implemented ... more Here we describe mechanisms for a half-dozen or so different types of learning to be implemented in “conscious” software agents, and speculate briefly on their implications for human learning and development. In particular, we're concerned with conceptual learning and behavioral learning in two “conscious” software agents, namely, CMattie and IDA. We offer computational mechanisms for such learning.
Individual Anticipatory Frameworks-Cognitively Inspired Anticipatory Adaptation and Associated Learning Mechanisms for Autonomous Agents
Lecture Notes in Computer Science, 2007
Virtual Mattie--an Intelligent Clerical Agent
AAAI Symposium on …, Aug 1, 1996
One important role for autonomous agents is to assume tasks previously performed by humans. Such ... more One important role for autonomous agents is to assume tasks previously performed by humans. Such tasks often require communication with humans, and the coordination of multiple activities. What sort of agent architecture will empower an agent to collaborate with ...
Knowledge Engineering Review, Dec 1, 2009
selectivity. The restriction of selectivity is mainly compelled by the specific characteristics o... more selectivity. The restriction of selectivity is mainly compelled by the specific characteristics of large-scale multi-agent systems. In such settings, it is reasonable to assume that the overhearing resources will be essentially limited, thus allowing the overhearing agent to overhear only a subset of inter-agent communications. Most previous investigations on overhearing ignore the limitation of selectivity, assuming that all relevant interagent communications can be overheard. In contrast, our work provides an empirical study of selective overhearing committed by both centralized and distributed teams of collaborative overhearing agents.
Human information agents include insurance agents, travel agents, voter registrars, mail-order se... more Human information agents include insurance agents, travel agents, voter registrars, mail-order service clerks, telephone information operators, employment agents, AAA route planners, customer service agents, bank loan officers, and many, many others. Such human agents must typically possess a common set of skills. These would often include most of the following:
Decision Making System for Cognitive Machines
There are ongoing efforts to build machines that behave with human-type intelligence in their sen... more There are ongoing efforts to build machines that behave with human-type intelligence in their sense-decide-act routines. Decision making in machines, integrated into the continuous interaction with its environment, is regarded as a process of choosing (from multiple alternatives) the controlling behavior. This book discusses a cognitively inspired decision making mechanisms (action selection, automatization, non-routine problem solving) that selects the next action with different levels of awareness: automatized skills, consciously mediated routine decisions, and consciously deliberated non-routine decisions; as well as the role of expectation/anticipation in facilitating intelligent behavior. The major challenge in any system is in building the whole out of the parts. This book contributes towards a general intelligence system, which integrates the decision making and other cognitive modules including perception, memory, attention, and “consciousness.” This integrative approach sho...
Information capacity and fault tolerance of binary weights Hopfield nets
Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)
ABSTRACT
Automatization for Software Agents
Page 1. Automatization for Software Agents Aregahegn Negatu Stan Franklin Lee McCauley Page 2. Wh... more Page 1. Automatization for Software Agents Aregahegn Negatu Stan Franklin Lee McCauley Page 2. What is automatization? • Automatization – a cognitive function to learn procedural tasks via experience/practice. • Examples: – Driving – Walking – Cycling – Swimming – Typing • Advantages: – Performance improves • parallel, without limited capacity. • or without mental effort. • Disadvantages: – Inflexibility. – Resistance to modification. Page 3. Automatization characteristics • implicit learning – automatic, but it requires conscious information ...
Proceedings of SSGRR-2001: International Conference on Advances in Infrastructure for e-Business, e-Education and e-Science on the Internet (L'Aquila, Italy), Aug 6, 2001
Abstract-In this paper, we describe mechanisms for several different types of learning being impl... more Abstract-In this paper, we describe mechanisms for several different types of learning being implemented in “conscious” software agents. We argue that in complex, dynamic domains, such learning mechanisms are essential for software agents to adapt and effectively 'live'in those domains. We further believe that a development period is required for knowledge acquisition. Particularly, in complex, dynamic domains where knowledge engineering is expensive, the development period provides a simple, but cost effective solution to ...
Workshop on Motor Development: Proceeding of Adaptation in Artificial and Biological Systems, AISB'06, 2006
In this paper we attempt to develop mechanisms for procedural memory and procedural learning for ... more In this paper we attempt to develop mechanisms for procedural memory and procedural learning for cognitive robots on the basis of what is known about the same facilities in humans and animals. The learning mechanism will provide agents with the ability to learn new actions and action sequences with which to accomplish novel tasks.
Cognitive Science Quarterly, 2002
In this paper we describe an action selection mechanism for a" conscious" software agen... more In this paper we describe an action selection mechanism for a" conscious" software agent. We discuss briefly the main cognitive modules of our agent architecture. Our focus is on the operational/functional details of the “consciousness” module and the action selection mechanism and how these two work together. We describe how events come to “consciousness,” how “conscious” events prime and bind to relevant actions/action-plans, and how the most relevant behavior/action is selected and executed. Our mechanisms ...
Sumpy: A fuzzy software agent
Proceedings of the ISCA Conference on Intelligent Systems, Jun 1, 1996
SUMPY is a software agent “living” in and helping to maintain a UNIX file system for better disk ... more SUMPY is a software agent “living” in and helping to maintain a UNIX file system for better disk space utilization by compressing and backing up. Built using subsumption architecture, SUMPY displays a “plug and play” property. A new UNIX maintenance task can be added to SUMPY's repertoire without modification of existing layers. One of SUMPY's layers sports a fuzzy control mechanism enabling it to achieve its goals in a realworld manner. Another restricts SUMPY's activity to times of slow CPU use. An experiment in ...
Proceedings of the International Conference on Security and Cryptography, 2010
Various security mechanisms are available to validate, authenticate and permit codes, data and sc... more Various security mechanisms are available to validate, authenticate and permit codes, data and scripts for executing in a computing device. Accordingly, different techniques and tools have been developed to preserve integrity and confidentiality at the process, protocol, system and communication levels. For example, Trusted Platform Module, Intel Trusted Execution Technology and Windows Vista Kernel Mode security ensure system level integrity and security, whereas, Digital Signature, Code Signing, Watermarking, Integrity Checker and Magic Cookies address integrity of data and executables in transit. A brief survey of these techniques is described here with how these techniques help to secure computing environment.
The Knowledge Engineering Review, 2009
selectivity. The restriction of selectivity is mainly compelled by the specific characteristics o... more selectivity. The restriction of selectivity is mainly compelled by the specific characteristics of large-scale multi-agent systems. In such settings, it is reasonable to assume that the overhearing resources will be essentially limited, thus allowing the overhearing agent to overhear only a subset of inter-agent communications. Most previous investigations on overhearing ignore the limitation of selectivity, assuming that all relevant interagent communications can be overheard. In contrast, our work provides an empirical study of selective overhearing committed by both centralized and distributed teams of collaborative overhearing agents.
Proceedings of SSGRR-2001: International Conference on Advances in Infrastructure for e-Business, e-Education and e-Science on the Internet (L'Aquila, Italy), Aug 6, 2001
Abstract-In this paper, we describe mechanisms for several different types of learning being impl... more Abstract-In this paper, we describe mechanisms for several different types of learning being implemented in “conscious” software agents. We argue that in complex, dynamic domains, such learning mechanisms are essential for software agents to adapt and effectively 'live'in those domains. We further believe that a development period is required for knowledge acquisition.
In this paper, we present LIDA, a working model of, and theoretical foundation for, machine consc... more In this paper, we present LIDA, a working model of, and theoretical foundation for, machine consciousness. LIDA’s architecture and mechanisms were inspired by a variety of computational paradigms and LIDA implements the Global Workspace Theory of consciousness. The LIDA architecture’s cognitive modules include perceptual associative memory, episodic memory, functional consciousness, procedural memory and action-selection. Cognitive robots and software agents controlled by the LIDA architecture will be capable of multiple learning mechanisms. With artificial feelings and emotions as primary motivators and learning facilitators, such systems will ‘live’ through a developmental period during which they will learn in multiple, human-like ways to act effectively in their environments. We also provide a comparison of the LIDA model with other models of consciousness.
Here we describe mechanisms for a half-dozen or so different types of learning to be implemented ... more Here we describe mechanisms for a half-dozen or so different types of learning to be implemented in “conscious” software agents, and speculate briefly on their implications for human learning and development. In particular, we're concerned with conceptual learning and behavioral learning in two “conscious” software agents, namely, CMattie and IDA. We offer computational mechanisms for such learning.
Cognitively inspired anticipatory adaptation and associated learning mechanisms for autonomous agents
Anticipatory Behavior in Adaptive Learning Systems, 2007
This paper describes the integration of several cognitively inspired anticipation and anticipator... more This paper describes the integration of several cognitively inspired anticipation and anticipatory learning mechanisms in an autonomous agent architecture, the Learning Intelligent Distribution Agent (LIDA) system. We provide computational mechanisms and experimental simulations for variants of payoff, state, and sensorial anticipatory mechanisms.
Uploads
Papers by Aregahegn Negatu