## Data Visualization and Feature Selection: New Algorithms for Nongaussian Data (1999)

Venue: | in Advances in Neural Information Processing Systems |

Citations: | 22 - 1 self |

### BibTeX

@INPROCEEDINGS{Yang99datavisualization,

author = {Howard Hua Yang and John Moody},

title = {Data Visualization and Feature Selection: New Algorithms for Nongaussian Data},

booktitle = {in Advances in Neural Information Processing Systems},

year = {1999},

pages = {687--693},

publisher = {MIT Press}

}

### Years of Citing Articles

### OpenURL

### Abstract

Data visualization and feature selection methods are proposed based on the joint mutual information and ICA. The visualization methods can find many good 2-D projections for high dimensional data interpretation, which cannot be easily found by the other existing methods. The new variable selection method is found to be better in eliminating redundancy in the inputs than other methods based on simple mutual information. The efficacy of the methods is illustrated on a radar signal analysis problem to find 2-D viewing coordinates for data visualization and to select inputs for a neural network classifier. Keywords: feature selection, joint mutual information, ICA, visualization, classification. 1 INTRODUCTION Visualization of input data and feature selection are intimately related. A good feature selection algorithm can identify meaningful coordinate projections for low dimensional data visualization. Conversely, a good visualization technique can suggest meaningful features to include ...

### Citations

529 | A new learning algorithm for blind signal separation
- Amari, Cichocki, et al.
- 1996
(Show Context)
Citation Context ...ransform a set of variables into a new set of variables, so that statistical dependency among the transformed variables is minimized. The version of ICA that we use here is based on the algorithms in =-=[1, 8]-=-. It discovers a non-orthogonal basis that minimizes mutual information between projections on basis vectors. We shall compare these methods in a real world application. 4 Application to Signal Visual... |

458 |
separation of sources, part I: An adaptive algorithm based on neuromimetric architecture
- Jutten, Herault
- 1991
(Show Context)
Citation Context ...it is better for analyzing nongaussian data. Both CCA and maximum joint MI are supervised methods while the PCA method is unsupervised. An alternative to these methods is ICA for visualizing clusters =-=[5]-=-. The ICA is a technique to transform a set of variables into a new set of variables, so that statistical dependency among the transformed variables is minimized. The version of ICA that we use here i... |

215 | Using mutual information for selecting features in supervised neuralnet learning
- Battiti
- 1994
(Show Context)
Citation Context ...tion processes, we need modelindependent approaches to select input variables before model specification. One such approach is ffi -Test [7]. Other approaches are based on the mutual information (MI) =-=[2, 3, 4]-=- which is very effective in evaluating the relevance of each input variable, but it fails to eliminate redundant variables. In this paper, we focus on the model-independent approach for input variable... |

119 | Adaptive online learning algorithms for blind separation: maximum entropy and minimum mutual information," Neural computation 9
- Yang, Amari
- 1997
(Show Context)
Citation Context ...ransform a set of variables into a new set of variables, so that statistical dependency among the transformed variables is minimized. The version of ICA that we use here is based on the algorithms in =-=[1, 8]-=-. It discovers a non-orthogonal basis that minimizes mutual information between projections on basis vectors. We shall compare these methods in a real world application. 4 Application to Signal Visual... |

75 | Prediction Risk and Architecture Selection for Neural Networks
- Moody
- 1994
(Show Context)
Citation Context ...ot only severely complicate the model selection/estimation process but also damage the performance of the final model. Selecting input variables after model specification is a model-dependent approach=-=[6]-=-. However, these methods can be very slow if the model space is large. To reduce the computational burden in the estimation and selection processes, we need modelindependent approaches to select input... |

34 | Finding the embedding dimension and variable dependencies in time series
- Pi, Peterson
- 1994
(Show Context)
Citation Context ... To reduce the computational burden in the estimation and selection processes, we need modelindependent approaches to select input variables before model specification. One such approach is ffi -Test =-=[7]-=-. Other approaches are based on the mutual information (MI) [2, 3, 4] which is very effective in evaluating the relevance of each input variable, but it fails to eliminate redundant variables. In this... |

8 |
A Mutual Information Measure for Feature Selection with Application to Pulse Classification
- Barrows, Sciortino
- 1996
(Show Context)
Citation Context ...tion processes, we need modelindependent approaches to select input variables before model specification. One such approach is ffi -Test [7]. Other approaches are based on the mutual information (MI) =-=[2, 3, 4]-=- which is very effective in evaluating the relevance of each input variable, but it fails to eliminate redundant variables. In this paper, we focus on the model-independent approach for input variable... |

6 | Nonparametric selection of input variables for connectionist learning
- Bonnlander
- 1996
(Show Context)
Citation Context ...tion processes, we need modelindependent approaches to select input variables before model specification. One such approach is ffi -Test [7]. Other approaches are based on the mutual information (MI) =-=[2, 3, 4]-=- which is very effective in evaluating the relevance of each input variable, but it fails to eliminate redundant variables. In this paper, we focus on the model-independent approach for input variable... |