Please do NOT rely on these kind of GenAI translations!
While the translation of what the slide says and what Dominik Blum says from 9:08 min are fine,
the other excerpts contain sentences with inaccuracies,
random additional words that cannot be found in the original (eg. there is no “for example” in what he says from 13:13 min and neither does he say “great” after “thank you” in the end nor does he talk about “making” neuromorphic computing “event-based” at 13:31 min - rather he says that event-based cameras are “basically predestined to be combined with spiking neural networks”)
or are even outright false, like claiming he allegedly said “With normal cameras, every single pixel is independent of the others”. Which obviously doesn’t make sense, as conventional cameras are frame-based.
What he really says is: “Die Event-Based-Kamera arbeitet grundlegend anders als normale, uns bekannte Kameras. Jedes einzelne Pixel ist unabhängig voneinander, und das hat bestimmte Vorteile.”
“The event-based camera works in a fundamentally different way from normal cameras we are familiar with. Each individual pixel is independent of each other, and that has certain advantages.”
The whole paragraph from 12:32 min is also badly translated. [I’m well aware my translation is not perfect, but definitely heaps better than ChatGPT’s…]
Its context is a presentation slide titled
“NMC is a young field of research…with many open questions, eg.”
Dominik Blum briefly addresses the following three questions: Which neuron model do I implement? How do I interpret spike data? How do I train spiking neural networks?
And then he adds a fourth point in reference to the table showing various neuromorphic hardware: “I can (= one can/you can) occupy myself (oneself/yourself) with developing neuromorphic hardware, and of course there are many more points, those were just the first ones.
I asked myself what was the first thing I had given thought to/investigated.
[Next presentation slide with Gartner’s Impact Radar comes up.]
Yes, erm, okay… Gartner placed neuromorphic computing in his Impact Radar where?
[Looks at presentation slide.] To “high” “mass”, in three to six years. Anyway, in any case you can imagine that it’s gonna be an exciting future with the development
…”
O-Ton [ziemlich wortgetreu, aber am besten selber mal anhören; da klingt das Ganze dann deutlich natürlicher als bei so einer lautsprachlichen Transkription]:
„Ich kann mich mit neuromorpher Hardware beschäftigen, mit der Entwicklung. Also, und es gibt natürlich noch viel mehr Punkte, einfach - das waren so die ersten. Ich hab’ überlegt, was war das erste, worüber ich nachgedacht habe.
[Nächste Präsentationsfolie mit Gartners Impact Radar erscheint.] Ja, ähm, gut. Gartner hat, äh, in seinem Impact Radar Neuromorphic Computing, äh, wohin gesetzt?
[Guckt auf die Präsentationsfolie.] Auf „high“ „mass“, in drei bis sechs Jahren. Wie auch immer, auf jeden Fall kann man sich vorstellen, dass das eine spannende Zukunft, äh, gibt mit der Entwicklung …“
. Don't let the dribble from some get in the way of great research.
