AntiLearning Signature in Biological Classification

1
Anti-Learning Signature in Biological
Classification

• Adam Kowalczyk
• Statistical Machine Learning
• NICTA, Canberra
• (Adam.Kowalczyk_at_nicta.com.au)

National ICT Australia Limited is funded and
supported by
1
2
Definition of anti-learning
Systematically
Random guessing accuracy
Off-training accuracy
Training accuracy
3
Learning and anti-learning mode of supervised
classification
4
Anti-learning in Low Dimensions
-1
1
1
-1
5
Anti-learning in Cancer Genomics
6
Predicting CRT response to Oesophageal carcinoma
7
Predicting CRT response
cDNA microarray data (from biopsies)
(LOO test)
8
Prediction of CRT response
) using data as of Nov. 2004
9
Anti-learning in Classification of Genes in Yeast

10
KDD02 task identification of Aryl Hydrocarbon
Receptor genes (AHR data)
11
Anti-learning in AHR-data set from KDD Cup 2002
Average of 100 trials random splits training
test 66 34
12
KDD Cup 2002 Yeast Gene Regulation Prediction
Taskhttp//www.biostat.wisc.edu/craven/kddcup/ta
sk2.ppt
13
Anti-learning in High Dimensional Approximation
(Mimicry)
14
Mimicry in High Dimensional Spaces
15
Quality of mimicry
d 1000
nE / nX
Average of independent test for of 50 repeats
16
Formal result
17
Proof idea 1 Geometry of the mimicry data
18
Proof idea 3kernel matrix
19
Hadamard Matrix

20
CS-kernels
Kowalczyk, Chapelle ALT05
21
Anti-learning in classification of Hadamard
dataset
Kowalczyk, Smola
22
Perfect anti-learning theorem
Kowalczyk, Smola, submitted
23
Perfect anti-learning i.i.d. a learning curve
n 100, nRand 1000
random

AROC mean std
2
1
4
5
0
3


nsamples i.i.d. samples from the perfect
anti-learning-set S
24
Conclusions

• Statistics and machine learning are indispensable
  components of forthcoming revolution in medical
  diagnostics based on genomic profiling
• High dimensionality of the data poses new
  challenges pushing statistical techniques into
  uncharted waters
• Challenges of biological data can stimulate novel
  directions of machine learning research

25
Acknowledgements

• Telstra
• Bhavani Raskutti
• Peter MacCallum Cancer Centre
• David Bowtell
• Coung Duong
• Wayne Phillips
• MPI
• Cheng Soon Ong
• Olivier Chapelle
• NICTA
• Alex Smola