Extracting and Composing Robust Features with Denoising Autoencoders

Extracting and Composing Robust Features with Denoising Autoencoders

[DBN] Learning multiple layers of Features from tiny images

Download now or preview on posterous

learning-features-2009-TR.pdf (4107 KB)

In this paper, there are more detailed equation derivations for RBM, especially the Gaussian-Bernoulli RBM.

 

Posted via email from Troy's posterous

Matlab v7.3 mat file and python

From: http://mloss.org/community/blog/2009/nov/19/matlabtm-73-file-format-is-actually-hdf5-and-can-b/

It looks like that matlab version 7.3 and later are capable of writing out objects in the so called matlab 7.3 file format. While at first glance it looks like another proprietary format - it seems to be in fact the Hierarchical Data Format version 5 or in short hdf5.

So you can do all sorts of neat things:

1. Lets create some matrix in matlab first and save it:

   >> x=[[1,2,3];[4,5,6];[7,8,9]] x = 1 2 3 4 5 6 7 8 9 >> save -v7.3 x.mat x

2. Lets investigate that file from the shell:

   $ h5ls x.mat x Dataset {3, 3} $ h5dump x.mat HDF5 "x.mat" { GROUP "/" { DATASET "x" { DATATYPE H5T_IEEE_F64LE DATASPACE SIMPLE { ( 3, 3 ) / ( 3, 3 ) } DATA { (0,0): 1, 4, 7, (1,0): 2, 5, 8, (2,0): 3, 6, 9 } ATTRIBUTE "MATLAB_class" { DATATYPE H5T_STRING { STRSIZE 6; STRPAD H5T_STR_NULLTERM; CSET H5T_CSET_ASCII; CTYPE H5T_C_S1; } DATASPACE SCALAR DATA { (0): "double" } } } } }

3. And load it from python:

   >>> import h5py >>> import numpy >>> f = h5py.File('x.mat') >>> x=f["x"] >>> x <HDF5 dataset "x": shape (3, 3), type "<f8"> >>> numpy.array(x) array([[ 1., 4., 7.], [ 2., 5., 8.], [ 3., 6., 9.]])

So it seems actually to be a good idea to use matlab's 7.3 format for interoperability.

Posted via email from Troy's posterous

[Deep] Deep learning tutorial on MLSS 2010

Download now or preview on posterous

Frean1.pdf (11467 KB)

More about MLSS 2010 could be found http://mlss10.rsise.anu.edu.au/proceedings

Posted via email from Troy's posterous

[ASR] Still Tandem systems

Download now or preview on posterous

combining phonetic attributes using conditional random field.pdf (112 KB)

The attached paper models phonetic attributes with CRF models. However, the sentence interests me most is the following one:

As described in [1] we used the linear output of the MLPs with a KL transform applied to them to decorrelate the features, as this gave the best results for the HMM system.

[1] H. Hermansky, D. Ellis, and S. Sharma, "Tandem connectionist feature stream extraction for conventional HMM systems", in Proc. of the ICASSP 2000.

Maybe sometime we could also try to refine the posterior features from NN for HMM systems. 

Posted via email from Troy's posterous

[Linux] Mac configure type

From: http://macosx.com/forums/unix-x11/29486-guessing-host-type-since-10-2-4-a.html

http://hints.macworld.com/article.php?story=2001041322081284

In many cases the build step involves running a configure script. Occasionally you'll run a configure script that gives error message stating that the host type cannot be determined. In such a case, you can usually either specify the configure option --host=powerpc-apple-darwin6.4 as I've done in the examples below. (Note in this case, we are using darwin6.4. To determine the correct release of darwin, enter the command uname -r.) You can alternatively copy two files into the build directory, that is, into the same directory that contains the script configure. 

Code:

cp /usr/share/libtool/config.guess . cp /usr/share/libtool/config.sub .

Occasionally, the configure option --build=powerpc-apple-darwin6.4 is needed to produce the desired result (again assuming we're using darwin release 6.4). 

In some cases, there are additional steps to be performed. ...

Posted via email from Troy's posterous

[Info] Machine Learning Summer School 2009

http://mlg.eng.cam.ac.uk/mlss09/

Posted via email from Troy's posterous