Deep Learning, or more specifically a subgroup of Deep Learning called (Deep) Convolutional Neural Networks have had impressive improvements since Alex Krizhevsky’s 2012 publication about (what is now called) AlexNet. AlexNet won the ImageNet Image Recognition competition with the (then close to jawdropping) top-5 error rate of only 17.0% (top-5 error means that if your classifier presents 5 answers at least one of them must be the correct one).
But Image Recognition accuracy have increased many times since then, i.e. from 17% in 2012 to 3.08% in 2016 (see publications in table below to see more about what the error rates mean and how they can be compared).
To put this into context: human beings perform at 5.10% error rate on this Image Recognition task, see Andrej Karpathy’s publication below (to be precise: at least 1 smart, trained and highly education human being performed at that error rate on the ImageNet task).
So what I am saying is that computers with Deep Learning can actually see and understand what is on a picture better than humans! (in some and probably most/all cases)
|2012||17.00||ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)||Alex Krizhevsky et. al||University of Toronto|
|2014||6.66||Going Deeper with Convolutions||Christian Szegedy et. al|
|2014 (Sep)||5.10||What I learned from competing against a ConvNet on ImageNet||Andrej Karpathy||Stanford University|
|2015 (Feb)||4.94||Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification||Kaiming He et. al||Microsoft Research|
|2015 (Dec)||3.57||Deep Residual Learning for Image Recognition||Kaiming He et. al||Microsoft Research|
|2016 (Feb)||3.08||Inception v4, Inception-ResNet and the Impact of Residual Connections on Learning||Christian Szegedy et. al|
Implications of better-than-human-level image recognition with Deep Learning?
Deep Convolutional Neural network research field has moved so fast that applications still lag behind on using this. Most robots/drones and software in servers, laptops, mobiles, wearables and medical equipment does not take advantage of these research results yet, but there is a huge untapped potential (will get back to the potential in later postings).
But there are some highly important applications already, e.g. the Samsung Medison RS80A Ultrasound Machine (see image in start of posting) that uses convolutional neural networks for Breast Cancer Diagnosis.
Next blog post is probably going to be about some (simple) analogies to explain the mechanics of Convolutional Neural Networks. Stay tuned and sign up for DeepLearning.Education mailing list below.