This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
assignments:assignment3 [2013/10/04 21:06] asa |
assignments:assignment3 [2013/10/06 11:54] asa |
||
---|---|---|---|
Line 10: | Line 10: | ||
Hint: consider the difference in the constraints. | Hint: consider the difference in the constraints. | ||
- | Discuss the merit of the bias-less formulation as the dimensionality | + | ===== Part 2: Closest Centroid Algorithm ===== |
- | of the data (or the feature space) is varied. | + | |
- | When using this SVM formulation it may be useful to add a constant to the | + | |
- | kernel matrix. Explain why this can be beneficial. | + | |
+ | Express the closest centroid algorithm in terms of kernels, i.e. determine how the $alpha_i$ coefficients will be determined using a given labeled dataset. | ||
- | ===== Part 3: Using the SVM ===== | + | ===== Part 3: Using SVMs ===== |
+ | |||
+ | The data for this question comes from a database called SCOP (structural | ||
+ | classification of proteins), which classifies proteins into classes | ||
+ | according to their structure (download it from {{assignments:scop_motif.data|here}}. | ||
+ | The data is a two-class classification | ||
+ | problem | ||
+ | of distinguishing a particular class of proteins from a selection of | ||
+ | examples sampled from the rest of the SCOP database. | ||
+ | I chose to represent the proteins in | ||
+ | terms of their motif composition. A sequence motif is a | ||
+ | pattern of nucleotides/amino acids that is conserved in evolution. | ||
+ | Motifs are usually associated with regions of the protein that are | ||
+ | important for its function, and are therefore useful in differentiating between classes of proteins. | ||
+ | A given protein will typically contain only a handful of motifs, and | ||
+ | so the data is very sparse. It is also very high dimensional, since | ||
+ | the number of conserved patterns in the space of all proteins is | ||
+ | large. | ||
+ | The data was constructed as part of the following analysis of detecting distant relationships between proteins: | ||
+ | |||
+ | * A. Ben-Hur and D. Brutlag. [[http://bioinformatics.oxfordjournals.org/content/19/suppl_1/i26.abstract | Remote homology detection: a motif based approach]]. In: Proceedings, eleventh international conference on intelligent systems for molecular biology. Bioinformatics 19(Suppl. 1): i26-i33, 2003. | ||
Download the dataset associated with this assignment from the homework | Download the dataset associated with this assignment from the homework | ||
Line 37: | Line 55: | ||
In this question we will consider both the Gaussian and polynomial kernels: | In this question we will consider both the Gaussian and polynomial kernels: | ||
$$ | $$ | ||
- | K_{gaus}(\mathbf{x}, \mathbf{x'} = \exp(-\gamma || \mathbf{x} - \mathbf{x}' ||^2) | + | K_{gaus}(\mathbf{x}, \mathbf{x'}) = \exp(-\gamma || \mathbf{x} - \mathbf{x}' ||^2) |
$$ | $$ | ||
$$ | $$ | ||
- | K_{poly}(\mathbf{x}, \mathbf{x'} = (1 + \mathbf{x}^T \mathbf{x}') ^{p} | + | K_{poly}(\mathbf{x}, \mathbf{x'}) = (1 + \mathbf{x}^T \mathbf{x}') ^{p} |
$$ | $$ | ||
Plot the accuracy of the classifier, measured using the success rate and the area under the ROC curve | Plot the accuracy of the classifier, measured using the success rate and the area under the ROC curve | ||
Line 53: | Line 71: | ||
polynomial kernel is not such a parameter). | polynomial kernel is not such a parameter). | ||
- | The data for this question comes from a database called SCOP (structural | ||
- | classification of proteins), which classifies proteins into classes | ||
- | according to their structure. The data is a two-class classification | ||
- | problem | ||
- | of distinguishing a particular class of proteins from a selection of | ||
- | examples sampled from the rest of the SCOP database. | ||
- | I chose to represent the proteins in | ||
- | terms of their motif composition. A sequence motif is a | ||
- | pattern of nucleotides/amino acids that is conserved in evolution. | ||
- | Motifs are usually associated with regions of the protein that are | ||
- | important for its function, and are therefore useful in predicting protein | ||
- | function. | ||
- | A given protein will typically contain only a handful of motifs, and | ||
- | so the data is very sparse. It is also very high dimensional, since | ||
- | the number of conserved patterns in the space of all proteins is | ||
- | large. | ||
- | More information about motifs and their usefulness in classifying | ||
- | proteins can be found in the following paper: | ||
- | |||
- | * A. Ben-Hur and D. Brutlag. Protein sequence motifs: Highly predictive features of protein function. In: Feature extraction, foundations and applications. I. Guyon, S. Gunn, M. Nikravesh, and L. Zadeh (eds.) Springer Verlag, 2006. | ||
For this type of sparse dataset it is useful to normalize the input features before | For this type of sparse dataset it is useful to normalize the input features before | ||
Line 79: | Line 77: | ||
accomplished in PyML by: | accomplished in PyML by: | ||
<code python> | <code python> | ||
- | data.normalize() | + | >>> data.normalize() |
</code> | </code> | ||
Compare the results under this normalization with what you obtain | Compare the results under this normalization with what you obtain | ||
Line 91: | Line 89: | ||
Explain the structure that you are seeing in the plot (it is more | Explain the structure that you are seeing in the plot (it is more | ||
interesting when the data is normalized). | interesting when the data is normalized). | ||
- |