-
I am looking at several alternatives to train a DBN on imagenet. My framework of choice would be Theano since it seems to be the most flexible. Is there an existing code I can build on that archives c…
-
We currently have most of the parameters used by InitialVotTrain and InitialVotDecode just hard-coded into the python helper scripts, e.g. epochs=2, loss_eps=4, min_vot_length=5 in training. The exce…
-
In case anyone cares enough to spend a moment fixing them:
```
auto_examples/applications/plot_outlier_detection_housing.rst:14: (vizualisation)
auto_examples/applications/plot_stock_market.rst:23: …
-
I get an error when installing. I am in a virtualenv using Python 3.4 on a Mac. Any idea why it fails to install?
``` bash
$ brew list --versions
aircrack-ng 1.1
android-sdk 22.3
apple-gcc42 4.2.1-5…
-
The licensing in individual files is a bit all over the place. Currently, we have the following (each followed by a list of the files it occurs in).
License: BSD3
- ./sklearn/tree/tree.py:
License: …
-
For precomputed kernels, a square matrix is not an efficient way to store the kernel matrix (since the kernel matrix is symmetric).
We should create a kernel object interface instead. Advantages:
- T…
-
I'm getting linking errors when compiling shogun 1.0.0:
```
(...)
./io/HDF5File.cpp.o: In function `MPI::Comm::Allreduce(void const*, void*, int, MPI::Datatype const&, MPI::Op const&) const':
/usr/in…