We have heard so much about deep learning in the media and elsewhere about the virtues of deep learning: from solving complicated computer vision problems to teaching computers to beat world-class Go players. But do we really need to jump into it? What are the advantages of deep learning over, say, other kinds of algorithms?
One of the areas of machine intelligence that has been more dramatically disrupted by the deep learning revolution is computer vision. For decades the field of computer vision has relied on carefully handcrafting features to improve the accuracy of algorithms, developing a rich theory and thousands of very domain-specific algorithms. With deep learning this has changed: given the right conditions, many computer vision tasks no longer require such careful feature crafting. Among such tasks we have image classification: teaching a machine to recognize the category of an image from a given taxonomy.
How hard image classification really is? In 2013, Kaggle launched a competition to classify pictures of cats and dogs, providing 12,500 images of each. According to this paper, the state of the art algorithms were expected to get an accuracy of around 80%. It turns out that the accuracy, using deep learning, was over 98%. How is that even possible?
ImageNet: where it all started
One of the earliest successes of deep learning is the ImageNet challenge. The ImageNet data set is a huge image library with over 1000 classes, curated by initiative of Fei-Feli Li, from the University of Illinois in Urbana-Champaign. Launched in 2010, the ImageNet challenge is a competition using this data set for researchers to evaluate the quality of their algorithms. Around 2011, the error rate was 25%. In 2012, using a deep learning architecture known as AlexNet, it was possible to reduce the error rate to 16%. The architecture of this network has been used over and over in different domains, as it has proven to be very successful. It is also possible to fine tune the trained network to adapt it to your application, so that you don’t need to retrain it every time!
Where are we now?
Deep learning has been successfully applied to a number of computer vision tasks, including image classification, and state-of-the-art results keep being published almost weekly by top labs on the world.
Some successful Czech startups include Spaceknow, which is applying deep learning for estimating economic indicators from satellite images and Rossum.ai with their very impressive technology for automating invoice processing. We can expect that deep learning will become more an integral part of the new generation of technology startups.