When being the first in your company to apply a deep learning algorithmon your data you often have to overcome several obstacles. One challengeis to understand your data and to form a training and test dataset.Another one is to get your algorithms and its performance accepted andintegrated in your existing processing workflow.Convolutional Neural Networks have become a standard tool in processingimage data. They have shown to reach human-level classificationperformance on some object recognition tasks.In this talk I will present my experiences in getting started using aconvolutional neural network for classification of 2D sensor data. Iwill point out the importance of understanding your data and give hintsof how to select your train and test datasets according to therequirements. Furthermore, I will show how to get a feature extractorout of the classifier and how to visualize it.
I would like to work with open source projects to create a branch of the tree with all
of the best videos for your open source project. Please
send me an email if you are interested.