Time in neural networks

Chappelier, Jean-Cédric; Grumbach, Alain

doi:10.1145/181911.181912

Cited by 13 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, from SVM theory, we can consider 1 for the model. Also, the model is formulated in terms of error variables, i.e, RLS-SVM training depends on the error between estimated output and actual output [7].…”

Section: A Recurrent Least-squares Support Vector Machinesmentioning

confidence: 99%

See 1 more Smart Citation

A Review on Temporal Reasoning Using Support Vector Machines

Madeo

Lima

Peres

2012

2012 19th International Symposium on Temporal Representation and Reasoning

View full text Add to dashboard Cite

Recently, Support Vector Machines have presented promissing results to various machine learning tasks, such as classification and regression. These good results have motivated its application to several complex problems, including temporal information analysis. In this context, some studies attempt to extract temporal features from data and submit these features in a vector representation to traditional Support Vector Machines. However, Support Vector Machines and its traditional variations do not consider temporal dependency among data. Thus, some approaches adapt Support Vector Machines internal mechanism in order to integrate some processing of temporal characteristics, attempting to make them able to interpret the temporal information inherent on data. This paper presents a review on studies covering this last approach for dealing with temporal information: incorporating temporal reasoning into Support Vector Machines and its variations.

show abstract

Section: A Recurrent Least-squares Support Vector Machinesmentioning

confidence: 99%

“…We have adopted a taxonomy discussed in [1] in order to organize different SVM approaches regarding temporal data analysis. First, as aforementioned, problems related to temporal analysis can be treated without considering, directly, temporal aspects of the data.…”

Section: Introductionmentioning

confidence: 99%

A Review on Temporal Reasoning Using Support Vector Machines

Madeo

Lima

Peres

2012

2012 19th International Symposium on Temporal Representation and Reasoning

View full text Add to dashboard Cite

show abstract

“…The hierarchy of models detailed hereafter is summarized in figure 1 (see also the paper of (Chappelier & Grumbach, 1994)). The hierarchy of models detailed hereafter is summarized in figure 1 (see also the paper of (Chappelier & Grumbach, 1994)).…”

Section: Time Integration In Connectionist Modelsmentioning

confidence: 99%

Sequence Learning

2001

Lecture Notes in Computer Science

View full text Add to dashboard Cite

PrefaceThis book is intended for use by scientists, engineers, and students interested in sequence learning in artificial intelligence, neural networks, and cognitive science. The book will introduce essential algorithms and models of sequence learning and develop them in various ways. With the help of these concepts, a variety of applications will be examined. This book will allow the reader to acquire an appreciation of the breadth and variety within the field of sequence learning and its potential as an interesting area of research and application. The reader is presumed to have basic knowledge of neural networks and AI concepts.Sequential behavior is essential to intelligence and a fundamental part of human activities ranging from reasoning to language, and from everyday skills to complex problem solving. Sequence learning is an important component of learning in many task domains -planning, reasoning, robotics, natural language processing, speech recognition, adaptive control, time series prediction, and so on. Naturally, there are many different approaches towards sequence learning. These approaches deal with different aspects of sequence learning. This book provides an overall framework for this field.

show abstract

“…Let us now detail the different approaches of time integration in connectionist models such as sketched out in the previous section. The hierarchy of models detailed hereafter is summarized in figure 1 (see also the paper of Chappelier and Grumbach (1994)).…”

Section: Time Integration In Connectionist Modelsmentioning

confidence: 99%