This Meetup is past

50 people went

Location image of event venue

Details

Let me invite you to Data Workshop #7.

You can check how it was on previous workshops:
• Data Workshop #1 (http://www.meetup.com/datakrk/events/230392309/)
• Data Workshop #2 (http://www.meetup.com/datakrk/events/231590232/)
• Data Workshop #3 (http://www.meetup.com/datakrk/events/232049478/)
• Data Workshop #4 (https://www.meetup.com/datakrk/events/233112089/)
• Data Workshop #5 (https://www.meetup.com/datakrk/events/234421443/)
• Data Workshop #6 (https://www.meetup.com/datakrk/events/237700232/)

Motivation
The Neural Network (especially Deep Learning) is very wide topic.

After the Artificial Intelligence winter (https://en.wikipedia.org/wiki/AI_winter) period, french neuronetologist, Yann Lecun (https://en.wikipedia.org/wiki/Yann_LeCun)figured out LeNet in 1998 - the network that allowed recognizing handwriting digits. But still CNN was known only to very narrow group of specialists. It has changed in 2012, when Alex Krizhevsky adopted the more advanced approach and built AlexNet… which won ImageNet competition. After 2012 the world changed and people saw the potential of CNN :).

CNN first of all is about computer vision, starting from face detection or object detection and ending on self-driving cars (which is very different type of task to predict next action). CNN can also be use in other areas for example in NLP (but it's another story).

What will you learn?
• Introduction to Convolution Neural Network (LeNet 5)
• Apply LeNet5 on MNIST (~96.8% accuracy)
• More advanced CNN & MNIST (~99.2% accuracy)
• Apply CNN on CIFAIR10
• Introduction to VGG{16,19}, ResNet50, Inception V3

About speaker
Vladimir likes traveling... also in the IT world. He worked in different areas in IT (with different technologies). Last 3-4 years he spends his time on learning and getting insights from the data. He was involved in building infrastructure for Big Data, he prepared an ETL (based on Hadoop stuff) and he made data prediction (sales forecasting) and many others. He learns from different MOOCs (Coursera, Udacity, edX and so on), books and he regularly participated in Kaggle's competitions. He loves (data) challenges.

Prerequisites
• Basic knowledge: python and data libraries (numpy and pandas)
• Three options:
[1] Auto-magic via docker - https://github.com/dataworkshop/environment
[2] Half-manual. The package manager “conda" - install through the Miniconda installer (http://conda.pydata.org/miniconda.html) or the Anaconda installer (https://www.continuum.io/downloads) + seaborn, keras, theano, tensorflow, hyperas, opencv
[3] Totally manually. Install manually those packages: jupyter, numpy, scikit-learn, pandas, matplotlib, seaborn, keras, theano, tensorflow, hyperas, opencv
Use this script to verify your environment: https://github.com/dataworkshop/prerequisite

To save some time, please run this command and download data before a meetup.
from keras.datasets import mnist, cifar10
_ = cifar10.load_data()
_ = mnist.load_data()

Please bring your laptop with you.
Please come an hour before if you need help with setting up the environment!
HOW TO GET TO THE MEETING?
By public transportation
You can reach our office by tram 4, 5, 9, 10, 52 or 72. The nearest stop is 'AWF'
and have a walk along Politechnika Krakowska buildings (Życzkowskiego street). Avia building is located at the end of this small street. Remember that total travel time from the city center may take around 30 minutes.
By car