modifs to docs/cifarSC2011

doc/cifarSC2011/boot_camp_overview.txt

@@ -2,38 +2,59 @@
 .. _cifar_summer_school2011_overview:
 
 
-******************************************
-Theano Boot Camp: CIFAR Summer School 2011
-******************************************
+========
+Schedule
+========
 
 
-Why follow this Theano Boot Camp?
----------------------------------
+Theano lab sessions will be in 4 x 90 minute blocks,
+on the afternoons of Aug 2, 3, 5, and 6 (but not Aug 4th).
 
- * *Explain why* Theano is a very usefull tool
- * *Teach* you Theano basic
- * *Show* how to use it on *recent machine learning* models
- * *Help you* build your first recent machine learning models in Theano
- * *If interest* can explain how to *easily extend Theano*
+Day 1
+-----
 
-Boot Camp Overview
-------------------
-
- * Day 1:
+ * Show of hands - what is your background?
 
  * Overview/Motivation
-   * ?!?!?show-of-hands regarding technical background questions
+
  * python/numpy crash course
+
  * Theano beggining
+
  * Example with recent ML models (DLT)
+
+day 1:
+I think that I could cover those 2 pages:
+ * http://deeplearning.net/software/theano/hpcs2011_tutorial/introduction.html
+ * http://deeplearning.net/software/theano/hpcs2011_tutorial/theano.html
+That include:
+ simple example
+ linear regression example with shared var
+ theano flags
+ grad detail
+ Symbolic variables
+ gpu
+ benchmarck
+
+Day 2
+-----
+
  * Day 2:
    * Loop/Condition in Theano (10-20m)
    * Propose/discuss projects
    * For groups and start projects!
+
+Day 3
+-----
+
  * Day 3: 
    * Advanced Theano(30 minutes)
       *  Debuging, profiling, compilation pipeline, inplace optimization
    * Projects / General hacking / code-sprinting.
+
+Day 4
+-----
+
  * Day 4: *You choose* (we can split the group)
      * Extending Theano or 
        * How to wrap code in an op
@@ -42,15 +63,3 @@ Boot Camp Overview
 
 
 
-day 1:
-I think that I could cover those 2 pages:
- * http://deeplearning.net/software/theano/hpcs2011_tutorial/introduction.html
- * http://deeplearning.net/software/theano/hpcs2011_tutorial/theano.html
-That include:
- simple example
- linear regression example with shared var
- theano flags
- grad detail
- Symbolic variables
- gpu
- benchmarck

doc/cifarSC2011/index.txt

 
 .. _index:
 
-=========================
-GPU programming made Easy
-=========================
+=========================================
+TheanoLab @ NCAP CIFAR Summer School 2011
+=========================================
+
+Aug 2-6, 2011, Toronto, Canada.
+
+
+Theano is python software for evaluating complicated array expressions.
+
+What does it do?
+
+ * aggressive expression optimizations,
+
+ * automatic GPU use, and
+
+ * symbolic differentiation.
+
+It complements the Python numeric/scientific software stack (e.g. numpy, scipy,
+scikits, matplotlib, PIL.)
+
+Design and feature set has been driven by research in the machine learning group at the University of
+Montreal (Yoshua Bengio, Pascal Vincent, Douglas Eck).
+Result: 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.
+
+It has proven to be useful for implementing:
+
+ - linear and nonlinear neural network classifiers
+
+ - convolutional models
+
+ - Energy models: RBM, DBN, GRBM, ssRBM, AIS
+
+ - Auto-encoders: DAE, CAE
+
+ - GP regression
+
+ - sparse coding
+
+ - recurrent neural networks, echo state, (HMM?)
+
+ - online and batch learning and optimization
+
+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.
+
+
+Contents
+--------
+
+The structured part of the course will be a walk-through of the following
+material. Interleaved with this structured part will be blocks of time for
+individual or group work.  The idea is that you can try out Theano and get help
+from gurus on hand if you get stuck.
 
 .. toctree::
 

doc/cifarSC2011/introduction.txt

@@ -6,19 +6,115 @@
 Introduction
 ************
 
-Theano motivations
+Background Questionaire
+-----------------------
+
+ * Who has used Theano before?
+
+   * What did you do with it?
+
+ * Who has used Python? numpy? scipy? matplotlib?
+
+ * Who has used iPython?
+
+   * Who has used it as a distributed computing engine?
+
+ * Who has done C/C++ programming?
+
+ * Who has organized computation around a particular physical memory layout?
+
+ * Who has used a multidimensional array of >2 dimensions?
+
+ * Who has written a Python module in C before?
+
+   * Who has written a program to *generate* Python modules in C?
+
+ * Who has used a templating engine?
+
+ * Who has programmed a GPU before?
+
+   * Using OpenGL / shaders ?
+
+   * Using CUDA (runtime? / driver?)
+
+   * Using PyCUDA ?
+
+   * Using OpenCL / PyOpenCL ?
+
+   * Other?
+
+ * Who has used Cython?
+
+
+Python in one slide
+-------------------
+
+Features:
+
+- General-purpose high-level OO interpreted language
+- Emphasizes code readability
+- Comprehensive standard library
+- Dynamic type and memory management
+
+Language things:
+
+- Indentation for block delimiters
+- Dictionary ``d={'var1':'value1', 'var2':42, ...}``
+- List comprehension: ``[i+3 for i in range(10)]``
+
+.. code-block: python
+
+    a = {'a': 5, 'b': None}   # dictionary of two elements
+    b = [1,2,3]               # list of three int literals
+
+    def foo(b, c=3):          # function w default param c
+        return a + b + c      # note scoping, indentation
+
+
+Numpy in one slide
 ------------------
-Theano tries to be the **holy grail** in computing: *easy to code* and *it fast to execute* !
 
-It works only on mathematical expressions, so you won't have:
+- Numpy provides a N-dimensional numeric array in Python
+- Well known basis for scientific computing
+- provides:
+  - elementwise computations
+  - linear algebra, Fourier transforms
+  - pseudorandom numbers from many distributions
+
+- Base scientific computing package in Python on the CPU
+- A powerful N-dimensional array object
+
+  - ndarray.{ndim, shape, size, dtype, itemsize, stride}
+  
+- Sophisticated broadcasting functions
+    
+  - ``numpy.random.rand(4,5) * numpy.random.rand(1,5)`` -> mat(4,5)
+  - ``numpy.random.rand(4,5) * numpy.random.rand(4,1)`` -> mat(4,5)
+  - ``numpy.random.rand(4,5) * numpy.random.rand(5)`` -> mat(4,5)
+
+- Tools for integrating C/C++ and Fortran code
+- Linear algebra, Fourier transform and pseudorandom number generation
+
+
+
+
+What's missing?
+---------------
+
+
+.. :
+
+    Theano tries to be the **holy grail** in computing: *easy to code* and *it fast to execute* !
+
+    It works only on mathematical expressions, so you won't have:
 
       - Function call inside a theano function
       - Structure, enum
       - Dynamic type (Theano is Fully typed)
 
-Unfortunately it doesn't do coffee... yet.
+    Unfortunately it doesn't do coffee... yet.
 
-.. image:: pics/Caffeine_Machine_no_background_red.png
+    .. image:: pics/Caffeine_Machine_no_background_red.png
 
 
 Theano status
@@ -117,34 +213,3 @@ Theano vs PyCUDA vs PyOpenCL vs CUDA
 - PyOpenCL (Python + OpenCL)
   - PyCUDA for OpenCL
 
-Python
-------
-
-- Interpreted language
-- General-purpose high-level programming language
-- OO and scripting language
-- Emphasizes code readability
-- Large and comprehensive standard library
-- Indentation for block delimiters
-- Dynamic type and memory management
-- Dictionary ``d={'var1':'value1', 'var2':42, ...}``
-- List comprehension: ``[i+3 for i in range(10)]``
-
-NumPy
------
-
-- Base scientific computing package in Python on the CPU
-- A powerful N-dimensional array object
-
-  - ndarray.{ndim, shape, size, dtype, itemsize, stride}
-  
-- Sophisticated broadcasting functions
-    
-  - ``numpy.random.rand(4,5) * numpy.random.rand(1,5)`` -> mat(4,5)
-  - ``numpy.random.rand(4,5) * numpy.random.rand(4,1)`` -> mat(4,5)
-  - ``numpy.random.rand(4,5) * numpy.random.rand(5)`` -> mat(4,5)
-
-- Tools for integrating C/C++ and Fortran code
-- Linear algebra, Fourier transform and pseudorandom number generation
-
-