--- a/project/templates/about/tutorial.html Thu Nov 24 17:42:13 2011 +0530
+++ b/project/templates/about/tutorial.html Wed Nov 30 13:25:05 2011 +0530
@@ -198,33 +198,48 @@
<h3 id="sec2.5">Ole Nielsen: Mapping and Geoprocessing with Python (2 hrs)</h3>
<ul>
<li>
- Putting information on a map and analyzing spatial data are fundamental to a
- wide range of areas such as navigation, working with climate or geological data,
- disaster management, presentation of modelling results, demographics, social networking etc.
+ Putting information on a map and analyzing spatial data are fundamental to a
+ wide range of areas such as navigation, working with climate or geological
+ data, disaster management, presentation of modelling results, demographics,
+ social networking etc. However, making and viewing maps is just the tip of
+ the iceberg: to communicate spatial information much work is needed under
+ the hood to read, write, manipulate and process the data underpinning the
+ maps.
</li>
<li>
- This tutorial will give a practical introduction to tools and techniques
- available for processing spatial information and, through a few hands-on
- exercises, give the participants a sense of how to manipulate and visualise
- spatial data using Python. Topics covered include reading and writing
- of important data formats for both raster and vector data, looking at the layers,
- awareness of issues with datums and projections, calculating centroids of polygons,
- calculation of distance between points on the surface of Earth, interpolation from raster
- grids to points etc. The tutorial has been developed for Ubuntu Linux and will provide source code,
- tests and data for this platform. However, the content and messages should be general and apply to any platform.
+ T This tutorial will give a practical introduction to tools and techniques
+ available for processing spatial information and, through hands-on
+ exercises, give the participants a sense of how to manipulate spatial data
+ using Python. Depending on time, topics covered include reading and writing
+ of important data formats for both raster and vector data, looking at the
+ layers with qgis, awareness of issues with datums and projections,
+ calculating area and centroids of polygons, performance enhancement using
+ vector operations, numerical stability issues, calculation of distance
+ between points on the surface of Earth, interpolation from raster grids to
+ points etc. The tutorial has been developed for Ubuntu Linux 11.04/11.10 and
+ will provide source code, tests and data for this platform. However, the
+ content and messages should be general and apply to any self-respecting
+ platform.
</li>
<li>
- I assume that participants know how to write and run
- Python scripts and would suggest you install qgis as well as
- the python dependencies numpy, matplotlib and gdal on your
- laptop. I don't assume any previous knowledge of mapping or Geographic Information Systems (GIS).
+ I assume that participants know how to write and run Python scripts and are
+ OK having a crack at implementing simple numerical operations such as
+ summations in Python. I don't assume any previous knowledge of mapping or
+ Geographic Information Systems (GIS). The tutorial depends on the
+ packages qgis and gdal-bin as well as the python dependencies python-numpy
+ and python-gdal which are preloaded on the distributed live-DVD. The
+ tutorial material itself will be available in the Subversion repository
+ http://oles-tutorials.googlecode.com/svn/trunk/scipy2011 and also on a USB
+ stick that I will bring along.
</li>
<li>
- If you have some spatial data you want to manipulate in Python feel free to bring it along and grab me during a lunch break.
+ If you have some spatial data you want to manipulate in Python feel free to
+ bring it along and grab me during a lunch break.
</li>
</ul>
+
<h3 id="sec2.6">Eric Jones: Traits + Traits UI (2 hrs)</h3>
<ul>
<li>
--- a/project/templates/talk/conf_schedule.html Thu Nov 24 17:42:13 2011 +0530
+++ b/project/templates/talk/conf_schedule.html Wed Nov 30 13:25:05 2011 +0530
@@ -28,7 +28,7 @@
<tr><td class="right">14:25-15:55</td><td class="left">Jayneil Dalal</td><td class="left"><a href="#sec2.8">Building Embedded Systems for Image Processing using Python</a></td></tr>
<tr><td class="right">15:55-16:25</td><td class="left">Kunal Puri</td><td class="left"><a href="#sec2.9">Smoothed Particle Hydrodynamics with Python</a></td></tr>
<tr><td class="right">16:25-16:45</td><td class="left">Nivedita Datta</td><td class="left"><a href="#sec2.10">Encryptedly yours : Python & Cryptography</a></td></tr>
-<tr><td class="right">16:45-17:30</td><td class="left">Gael</td><td class="left"><b>Invited</b></td></tr>
+<tr><td class="right">16:45-17:30</td><td class="left">Gael</td><td class="left"><a href="#sec2.23"><b>Machine learning as a tool for Neuroscience</b></td></tr>
</tbody>
</table>
@@ -335,4 +335,65 @@
<p>The paper is about how we can use python for writing tools for reverse engineering and assembly code analysis it will talk about basic and modules those are available for doing reverse engineering. </p>
<h4>Slides</h4>
<p>To be uploaded</p>
+
+<h3 id="sec2.23">Gael Varoquaux(Affiliation: INRIA Parietal, Neurospin, Saclay, France): Machine learning as a tool for Neuroscience</h3>
+<h4>Abstract</h4>
+<p>For now two decades, functional brain imaging has provided a tool for
+building models of cognitive processes. However, these models are
+ultimately introduced without a formal data analysis step. Indeed,
+cognition arise from the interplay of many elementary functions. There
+are an exponential amount of competing possible models, that cannot be
+discriminated with a finite amount of data. This data analysis problem is
+common in many experimental science settings, although seldom diagnosed.
+In statistics, it is known as the <b>curse of dimensionality</b>, and can be
+tackled efficiently with machine learning tools.</p>
+<p>
+For these reasons, imaging neuroscience has recently seen a
+multiplication of complex data analysis methods. Yet, machine learning is
+a rapidly-evolving research field, often leading to impenetrable
+publication and challenging algorithms, of which neuroscience data
+analysts only scratch the surface.
+</p>
+<p>
+I will present our efforts to foster a general-purpose machine-learning
+Python module, <b>scikit-learn</b>, for scientific data analysis. As it aims
+to bridge the gap between machine-learning researchers and end-users, the
+package is focused on ease of use and high-quality documentation while
+maintaining state-of-the-art performance. It is enjoying a growing
+success in research laboratories, but also in communities with strong
+industrial links such as web-analytics or natural language processing.
+</p>
+<p>
+We combine this module with high-end interactive
+visualization using <b>Mayavi</b> and neuroimaging-specific tools in <b>nipy</b> to
+apply state of the art machine learning techniques to neuroscience:
+learning from the data new models of brain activity, focused on
+predictive or descriptive power. These models can be used to perform
+"brain reading": predicting behavior our thoughts from brain images. This
+is a well-posed <b>supervised learning</b> problem. In <b>unsupervised</b>
+settings, that is in the absence of behavioral observations, we focus on
+learning probabilistic models of the signal. For instance, interaction
+graphs between brain regions at rest reveal structures well-known to be
+recruited in tasks.
+</p>
+<p>
+Optimal use of the data available from a brain imaging session raises
+computational challenges that are well-known in large data analytics. The
+<b>scipy</b> stack, including <b>Cython</b> and <b>scikit-learn</b>, used with care, can
+provide a high-performance environment, matching dedicated solutions. I
+will highlight how the *scikit-learn* performs efficient data analysis in
+Python.
+</p>
+<p>
+The challenges discussed here go beyond neuroscience. Imaging
+neuroscience is a test bed for advanced data analysis in science, as it
+faces the challenge of integrating new data without relying on
+well-established fundamental laws. However, with the data available in
+experimental sciences growing rapidly, high-dimensional statistical
+inference and data processing are becoming key in many other fields.
+Python is set to provide a thriving ecosystem for these tasks, as it
+unites scientific communities and web-based industries.
+</p>
+<h4>Slides</h4>
+<p>To be uploaded</p>
{% endblock content %}