Related Experiment Video
Updated: Jul 7, 2026
07:38
Two-Photon Polymerization 3D-Printing of Micro-scale Neuronal Cell Culture Devices
Published on: June 7, 2024
Modular neural networks for MAP classification of time series and the partition algorithm
1Dept. of Electr. Eng., Aristotelian Univ. of Thessaloniki.
IEEE Transactions on Neural Networks
|January 1, 1996
Summary
This study introduces a partition algorithm for time-series classification, using a hierarchical recurrent network to adaptively update source probabilities for accurate classification of deterministic and probabilistic data.
Area of Science:
- Artificial Intelligence
- Machine Learning
- Signal Processing
Background:
- Time-series classification is a critical task in various scientific domains.
- Existing methods may not effectively handle dynamic source changes or probabilistic data.
- A systematic approach for designing modular classification networks is needed.
Purpose of the Study:
- To present a novel partition algorithm for time-series classification.
- To implement this algorithm using a hierarchical, modular, recurrent network.
- To demonstrate its applicability to deterministic, probabilistic, and source-switching time series.
Main Methods:
- The partition algorithm computes posterior probabilities to classify time series.
- Prediction error adaptively updates the posterior probability of candidate sources.
- A hierarchical network with partition (prediction) and decision (classification) levels is employed.
Main Results:
- The proposed method successfully classifies time series based on computed posterior probabilities.
- The hierarchical network effectively integrates prediction and decision modules.
- Applications demonstrated include signal detection, phoneme classification, and enzyme classification.
Conclusions:
- The partition algorithm offers a systematic method for designing modular classification networks.
- The approach is versatile, applicable to various time-series types and includes source switching.
- The framework allows for extensions by modifying partition and decision components.
Related Concept Videos
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
01:31Classification of Systems-II
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
01:26Classification of Systems-I
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as: