Kurtzweil AI, Amara D. Angelica, An interview with Dr. Juergen Schmidhuber on the future of neural networks, November 28, 2012
AA: In several contests and machine-learning benchmarks, your team's NNs are now outperforming all other known methods. As The New York Times noted Friday, last year, a program your team created won a pattern recognition contest by outperforming both competing software systems and a human expert in identifying images in a database of German traffic signs.
The German Traffic Sign Benchmark (credit: Institut fur Neuroinformatik, Bochum)
The winning program accurately identified 99.46 percent of the images in a set of 50,000; the top score in a group of 32 human participants was 99.22 percent, and the average for the humans was 98.84 percent," the Times pointed out. Impressive. What is the importance of traffic sign recognition in this field?
JS: That was from the IJCNN 2011 Traffic Sign Recognition Competition. This is highly relevant for self-driving cars as well as modern systems for driver's assistance.
AA: What's your team's secret?
JS: Remarkably, we do not need the traditional sophisticated computer vision techniques developed over the past six decades or so. Instead, our deep, biologically rather plausible artificial neural networks (NNs) are inspired by human brains, and they learn to recognize objects from numerous training examples.
I discuss this in detail in a talk at AGI-2011, "Fast Deep/Recurrent Nets for AGI Vision" (only voice and slides though):
|Previous post||Next post|