Some update.

doc/omlw2014/gpundarray.txt

 
-.. _omlw2014_libgpundarray:
+.. _omlw2014_libgpuarray:
 
-*************
-libGpuNdArray
-*************
+***********
+libgpuarray
+***********
 
 Why a common GPU ndarray?
 -------------------------
@@ -36,7 +36,6 @@ Design Goals
 Final Note
 ----------
 
-TODO: update
-- Usable, but under development.
-- Is the next GPU array container for Theano
+- Usable directly, but not all implementation available.
+- Is the next GPU array container for Theano and is working (not all implementation available now)
 - Mailing list: http://lists.tiker.net/listinfo/gpundarray

doc/omlw2014/index.txt

 
 .. _omlw2014_index:
 
-===========================
-Theano Tutorial @ OMLW 2014
-===========================
+====================================================
+Theano/Pylearn2/libgpuarray Presentation @ OMLW 2014
+====================================================
 
 August 22, 2014, New York University, US.
 
-This presentation will talk about Theano, Pylearn2  software stack for
-machine learning.
+Theano, Pylearn2 and libgpuarray software stack for machine learning.
 
 It complements the Python numeric/scientific software stack (e.g. NumPy, SciPy,
 scikits, matplotlib, PIL.)
@@ -35,11 +34,12 @@ The result is a very good library for doing research in deep
 learning and neural network training, and a flexible framework for
 many other models and algorithms in machine learning more generally.
 
-# TODO UPDATE
 It has proven to be useful for implementing:
 
  - linear and nonlinear neural network classifiers
 
+   - including Maxout, Dropout
+
  - convolutional models
 
  - Energy models: RBM, DBN, GRBM, ssRBM, AIS
@@ -58,8 +58,8 @@ It has proven to be useful for implementing:
 
 As people's needs change this list will grow, but Theano is built
 around vector, matrix, and tensor expressions; there is little reason
-to use it for calculations on other data structures except. There is
-also sparse matrix support.
+to use it for calculations on other data structures except. It
+also support sparse matrix.
 
 
 Pylearn2
@@ -83,7 +83,7 @@ Pylearn2 Vision
   too much top-down planning in advance.
 * A machine learning toolbox for easy scientific experimentation.
 * All models/algorithms published by the LISA lab should have reference
-  implementations in Pylearn2.
+  implementations in Pylearn2. TODO REMOVE???
 * Pylearn2 may wrap other libraries such as scikits.learn when this is practical
 * Pylearn2 differs from scikits.learn in that Pylearn2 aims to provide great
   flexibility and make it possible for a researcher to do almost anything,
@@ -99,6 +99,37 @@ Pylearn2 Vision
 * Remain approachable enough to be used in the classroom
 
 
+libgpuarray
+===========
+
+Make a common GPU ndarray(matrix/tensor or n dimensions) that can be
+reused by all projects. It support CUDA and OpenCL.
+
+Motivation
+----------
+
+* Currently there are at least 6 different gpu arrays in python
+  *  CudaNdarray(Theano), GPUArray(pycuda), CUDAMatrix(cudamat), GPUArray(pyopencl), Clyther, Copperhead, ...
+  *  There are even more if we include other languages.
+
+* They are incompatible
+  * None have the same properties and interface.
+
+* All of them are a subset of numpy.ndarray on the gpu!
+
+
+Design Goals
+------------
+
+* Have the base object in C to allow collaboration with more projects.
+  * We want people from C, C++, ruby, R, ... all use the same base GPU ndarray.
+* Be compatible with CUDA and OpenCL.
+* Not too simple, (don't support just matrix).
+* But still easy to develop new code that support only a few memory layout.
+  * This easy the development of new code.
+
+
+
 Contents
 ========
 

doc/omlw2014/introduction.txt

@@ -79,51 +79,6 @@ NumPy in one slide
 Arrays can be combined with numeric operators, standard mathematical
 functions. NumPy has great `documentation <http://docs.scipy.org/doc/numpy/reference/>`_.
 
-Training an MNIST-ready classification neural network in pure NumPy might look like this:
-
-.. code-block:: python
-
-    #########################
-    # NumPy for Training a
-    # Neural Network on MNIST
-    #########################
-
-    x = np.load('data_x.npy')
-    y = np.load('data_y.npy')
-    w = np.random.normal(
-        avg=0,
-        std=.1,
-        size=(784, 500))
-    b = np.zeros((500,))
-    v = np.zeros((500, 10))
-    c = np.zeros((10,))
-
-    batchsize = 100
-    for i in xrange(1000):
-        x_i = x[i * batchsize: (i + 1) * batchsize]
-        y_i = y[i * batchsize: (i + 1) * batchsize]
-
-        hidin = np.dot(x_i, w) + b
-
-        hidout = np.tanh(hidin)
-
-        outin = np.dot(hidout, v) + c
-        outout = (np.tanh(outin) + 1) / 2.0
-
-        g_outout = outout - y_i
-        err = 0.5 * np.sum(g_outout) ** 2
-
-        g_outin = g_outout * outout * (1.0 - outout)
-
-        g_hidout = np.dot(g_outin, v.T)
-        g_hidin = g_hidout * (1 - hidout ** 2)
-
-        b -= lr * np.sum(g_hidin, axis=0)
-        c -= lr * np.sum(g_outin, axis=0)
-        w -= lr * np.dot(x_i.T, g_hidin)
-        v -= lr * np.dot(hidout.T, g_outin)
-
-
 What's missing?
 ---------------
 
@@ -236,7 +191,29 @@ Project status
 
  * Github (`bleeding edge` repository, the one recommanded): unknown
 
-* Github stats?????
+* TODO: Github stats?????
+
+
+Pylearn2 in one slide
+---------------------
+
+TODO
+
+Other global information
+------------------------
+
+Theano have small basic operation, not layers as base operation:
+
+* Easy reuse
+* Don't need to reimplement the grad for each variation of layers
+
+This could cause slowness (more small operation), but the optimizer fix that.
+
+Pylearn2 wrap the small operations into layers like other
+projects:
+
+* There is no overhead to this extra layer, due to the
+  compilation of the function by Theano.
 
 
 Why scripting for GPUs?

doc/omlw2014/sharing.txt

@@ -4,7 +4,7 @@
 Sharing code
 ************
 
-* License
-* Common base object?
-* If not, important implementation that use raw ptr/shape?
-* Important, acknowledgement section on web site AND in paper about the software.
+* License (BSD 3 clauses suggested, don't forget to add the license info in the code)
+* Common base object? libgpuarray.
+* If not, important implementation that use raw ptr/shape? Doc that interface.
+* Important, *acknowledgement section on web site*(citation like) AND *in paper* about the software we reuse! (and use too)