c3d2/c3d2-web
c3d2
/
c3d2-web
38
3
Fork 0
Code Issues 1 Pull Requests Releases Wiki Activity

Updated Talk for PyDresden

This commit is contained in:
Frank Becker 2017-08-21 20:52:15 +02:00
parent 36776f632f
commit 2d79accdf3
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
content/news/event-20170824-pydd.xml
View File

@ -1,7 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE item SYSTEM "http://www.c3d2.de/dtd/c3d2web.dtd">
<item title="Fünftes Treffen Python User Group Dresden" date="2017-08-07T23:13:37" author="a8">
<item title="Fünftes Treffen Python User Group Dresden - Deep Learning for Computer Vision" date="2017-08-07T23:13:37" author="a8">
<image title="Python User Group">python-lang.png</image>
<event>
<start>2017-08-24T19:00:00</start>
@ -13,8 +13,17 @@
Dieser Kreis dient dem Erfahrungsaustausch der Python User Group Dresden, auch unter <link href="http://pydresden.org/">pydresden.org</link> zu finden.
<!-- Der Termin findet regelmäßig in der 3. Kalenderwoche an wechselnden Kalendertagen statt -->
</p>
<p title="Convolutional Neural Networks for Image Classification">
Today we have Alex Conway as a guest who is presenting his talk <em>Convolutional Neural Networks for Image Classification</em>. The talk will be held in English.
<p>
Today we have Alex Conway as a guest who is presenting his talk <em>Deep Learning for Computer Vision</em>. The talk will be in English like its announcement is.
</p>
<p title="Deep Learning for Computer Vision">
The state-of-the-art in image classification has skyrocketed thanks to the development of deep convolutional neural networks and increases in the amount of data and computing power available to train them. The top-5 error rate in the international ImageNet competition to predict which of 1000 classes an image belongs to has plummeted from 28% error in 2010 before deep learning to just 2.25% in 2017 (human level error is around 5%).
</p>
<p>
In addition to being able to classify objects in images (including not hotdogs), deep learning can be used to automatically generate captions for images, convert photos into paintings, detect cancer in pathology slide images, and help self-driving cars ‘see’.
</p>
<p>
The talk will give an overview of the cutting edge in the field and some of the core mathematical concepts behind the models. It will also include a short code-first tutorial to show how easy it is to get started using deep learning for computer vision in python…
</p>
<p>
So, this is your chance to ask all the questions about machine learning that are circling in your head and discuss ideas.