The authors study the performance of feedforward artificial neural networks in forecasting future... more The authors study the performance of feedforward artificial neural networks in forecasting future values of several different time series. They explore both short- and long-term prediction of several periodic time series. They find that a significant source of error in long-term prediction of time series is introduced by a phase shift between the network output and the time series. They explore the origin of this phase shift and suggest strategies for minimizing its effect. They find that the phase diagrams of the time series and the neural network forecast contain useful diagnostic information.
International Journal of Systems Science, Apr 1, 1979
This paper investigates the advantages of combining the sensitivity analysis method of parameter ... more This paper investigates the advantages of combining the sensitivity analysis method of parameter estimation with a new computational method for the solution of systems of ordinary differential equations. It is shown that the new method allows one to take advantage of the fact that the sensitivity equations have the same structure as the model equations.
The purpose of this paper is to point out the need for performance evaluation measures and techni... more The purpose of this paper is to point out the need for performance evaluation measures and techniques suitable for the evaluation of specialized architectural features in nonnumeric applications. Toward this end, problems associated with the use of data base machines are examined at three levels of detail: the user level, the system level and the device level.
The International Conference on Artificial Neural Networks (ICANN) is the annual gathering organi... more The International Conference on Artificial Neural Networks (ICANN) is the annual gathering organized by the European Neural Network Society (ENNS) for neural network researchers, both European and non-European. The ENNS was established in Helsinki in June 1991, when the first ICANN was held under the direction of Teuvo Kohonen, one of the earliest pioneers of neural networks in Europe. The ENNS has steadily grown ever since, establishing along the way links with its sister societies: INNS and JNNS, the Internaitorial ...
This chapter discusses the language of system theory. The concept of “system” is as old as civili... more This chapter discusses the language of system theory. The concept of “system” is as old as civilization. A system is a collection of the objects that are united by some form of interaction or interdependence. A system might be regarded as a set of interrelated elements. The nature of elements that are involved and the relations that might exist among the elements depend upon the type of system under consideration. The fact that a system can be regarded as a set is useful because this allows one to draw freely from the edifice of knowledge that is available in set theory, topology, and function theory. The concept of a system can be traced back to antiquity; the “systems approach” concept appears to be of a recent origin. The phrase “systems approach” is associated with a cadre of disciplines that have arisen since World War II, the most familiar being operations research, management science, and systems analysis.
The purpose of this paper is to point out the need for performance evaluation measures and techni... more The purpose of this paper is to point out the need for performance evaluation measures and techniques suitable for the evaluation of specialized architectural features in nonnumeric applications. Toward this end, problems associated with the use of data base machines are examined at three levels of detail: the user level, the system level and the device level.
The authors study the performance of feedforward artificial neural networks in forecasting future... more The authors study the performance of feedforward artificial neural networks in forecasting future values of several different time series. They explore both short- and long-term prediction of several periodic time series. They find that a significant source of error in long-term prediction of time series is introduced by a phase shift between the network output and the time series. They explore the origin of this phase shift and suggest strategies for minimizing its effect. They find that the phase diagrams of the time series and the neural network forecast contain useful diagnostic information.
International Journal of Systems Science, Apr 1, 1979
This paper investigates the advantages of combining the sensitivity analysis method of parameter ... more This paper investigates the advantages of combining the sensitivity analysis method of parameter estimation with a new computational method for the solution of systems of ordinary differential equations. It is shown that the new method allows one to take advantage of the fact that the sensitivity equations have the same structure as the model equations.
The purpose of this paper is to point out the need for performance evaluation measures and techni... more The purpose of this paper is to point out the need for performance evaluation measures and techniques suitable for the evaluation of specialized architectural features in nonnumeric applications. Toward this end, problems associated with the use of data base machines are examined at three levels of detail: the user level, the system level and the device level.
The International Conference on Artificial Neural Networks (ICANN) is the annual gathering organi... more The International Conference on Artificial Neural Networks (ICANN) is the annual gathering organized by the European Neural Network Society (ENNS) for neural network researchers, both European and non-European. The ENNS was established in Helsinki in June 1991, when the first ICANN was held under the direction of Teuvo Kohonen, one of the earliest pioneers of neural networks in Europe. The ENNS has steadily grown ever since, establishing along the way links with its sister societies: INNS and JNNS, the Internaitorial ...
This chapter discusses the language of system theory. The concept of “system” is as old as civili... more This chapter discusses the language of system theory. The concept of “system” is as old as civilization. A system is a collection of the objects that are united by some form of interaction or interdependence. A system might be regarded as a set of interrelated elements. The nature of elements that are involved and the relations that might exist among the elements depend upon the type of system under consideration. The fact that a system can be regarded as a set is useful because this allows one to draw freely from the edifice of knowledge that is available in set theory, topology, and function theory. The concept of a system can be traced back to antiquity; the “systems approach” concept appears to be of a recent origin. The phrase “systems approach” is associated with a cadre of disciplines that have arisen since World War II, the most familiar being operations research, management science, and systems analysis.
The purpose of this paper is to point out the need for performance evaluation measures and techni... more The purpose of this paper is to point out the need for performance evaluation measures and techniques suitable for the evaluation of specialized architectural features in nonnumeric applications. Toward this end, problems associated with the use of data base machines are examined at three levels of detail: the user level, the system level and the device level.
Uploads
Papers by Rao Vemuri