DEEP LEARNING
Strides made in AI, but challenges remain
Greg Blackman reports on the deep learning discussions at Vision in Stuttgart
B
oth the award winners at this year’s Vision show in Stuttgart – Prophesee for the Vision Award and
GrAI Matter Labs for best start-up – were AI devices. In fact, of the 15 young companies pitching for best start-up, 10 mentioned AI. Neural networks have become a phenomenon and the solutions addressing industrial imaging and the pain points associated with production lines – the lack of pictures of defects and the challenges
of annotating data – are multiplying. Before announcing the Vision Award
winner, Martin Wäny of the judging panel picked out a few past winners, including AnaLogic, which won in 2003 for a neural network processing chip. Wäny said: ‘Back then it was debatable whether neural networks were suitable or usable for industrial vision and factory automation. Well, if you walk around this show it’s hard not to find a booth that doesn’t mention AI.’ Te VDMA and Messe Stuttgart organised
a panel session on the topic of deep learning at the show. Dr Dietmar Ley, CEO of Basler, said during the discussion: ‘We’ve made great strides in making deep learning more usable and more practical over the course of the last three years [since the last Vision show].’ He said: ‘Tree years ago it was difficult
10 IMAGING AND MACHINE VISION EUROPE OCTOBER/NOVEMBER 2021
to find the right tools and components to do deep learning properly, and at a reasonable cost point. We believe this has greatly changed.’ He went on to note the abundance of
processors now available for running neural networks, and not just GPUs, but processors dedicated for deep learning. As Dr Olaf Munkelt, managing director of MVTec Software, said: ‘Giants like Intel have built special neural network cores in their hardware. Te hope is that this becomes
‘Take images, take a lot of them, store them, learn how to organise them’
@imveurope |
www.imveurope.com
local_doctor/
Shutterstock.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32
