Anzeige
Anzeige

Intuition in a box?

Jeff Bier’s Embedded Vision Column

Since reading Malcolm Gladwell’s ‚Blink‘ a decade ago, I’ve been intrigued by how the mind works – particularly how judgements and decisions are made. I’ve been inspired to take an armchair tour of research on this topic, and have encountered fascinating insights from the likes of David Eagleman and Daniel Kahneman.
Reading the work of these talented researchers and writers has led me to the inescapable conclusion that most of our judgements and decision-making take place in our subconscious minds. I consider myself a hyper-rational engineering type, so the idea that my subconscious is calling the shots – based not on deliberation and calculation but rather on intuition – was initially uncomfortable. Lately, though, I’ve come to appreciate the value of intuition – the way it can alert me to a dangerous situation before I comprehend the nature of the danger, for example, or warn me that someone’s being untruthful before I’m able to identify the actual lie. And that has started me wondering: What if our devices, systems and applications could gain this type of intuitive insight? For example, what if a device could warn you that there’s been a change in your elderly parent’s posture or gait that might indicate an increased risk of falls? Or that your teenager’s distracted driving indicates a higher risk of an accident? Because our subconscious processes are by definition hidden from us, it might seem futile to try to create programs to emulate them. But I think that deep neural networks (the kind that have recently been beating humans at image classification tasks) offer an elegant solution. Creating a deep neural network to distinguish between classes of objects or events (for example, a genuine smile vs. a faked one) does not require devising an algorithm to mechanically emulate the mechanisms that enable humans to distinguish between these cases. Instead, the neural network acts as a generalized learning machine, and the developer trains it to recognize meaningful differences via large numbers of examples. One factor that’s held back the use of deep neural networks is processing power. It takes a humungous amount of processing power to train deep neural networks, and quite a lot to run them once trained. Only very recently has this type of processing power become available at practical prices – including in embedded processors suitable for high-volume, cost-sensitive products. Because deep neural networks are massively parallel structures, they are very suitable for acceleration using massively parallel architectures. And because they have simple, highly repetitive structures, they’re also amenable to acceleration via specialized architectures. As result, I think we can expect rapid improvements in cost-performance and energy-efficiency of processors for neural network applications – far outstripping the modest gains enabled by advances in chip manufacturing. This means that, very soon, developers of many types of systems, applications and devices will have the possibility of incorporating new types of intelligence into their products. But to do so, they’ll need to understand how deep neural networks work, how to design them, and how to train them. I believe that the combination of deep learning and computer vision will create world-changing products and bring vast opportunities, and I’m eager to harness it. If you’re interested in learning about deep neural networks and other computer vision topics, I invite you to join me at the Embedded Vision Summit on May 2-4 in Santa Clara, California. This event, an educational forum for product creators interested in incorporating visual intelligence into electronic systems and software, is organized by the Embedded Vision Alliance. For details about this unique conference, and to register, please visit our website.

Anzeige

Empfehlungen der Redaktion

Das könnte Sie auch interessieren

Wie könnte der EMVA1288 Standard auf neue Modalitäten erweitert werden, z.B. multimodale Bildsensoren oder Bildsensoren nicht-linearer Kennlinie?

Anzeige

www.emva.org

Anzeige

Wer Andere oder das Internet befragt hat, ob benötigte Kabellängen in der gewünschten Schnittstelle realisierbar sind, wird überrascht sein, wie viele unterschiedliche Antworten man für die gleiche Frage bekommen kann. Woran liegt das und was ist aktuell wirklich darstellbar?‣ weiterlesen

www.alysium.com

Anzeige

Antonio Belletti (Bild rechts) ist neuer Geschäftsführer von Leuze Electronic Italien. Nach insgesamt 18 Jahren übergibt damit Alessandro Rigerio (links) das Szepter, um selbst in den verdienten Ruhestand zu gehen. Belletti ist bereits seit 1. September an Bord und bringt über 15 Jahre Erfahrung als Sales Manager und Global Account Executiv auf dem italienischen Markt mit in seine neue Position.

leuze.com

Anzeige

GOM veranstaltet 2019 mehrere Veranstaltungen unter dem Titel ‚Wissensforum Kunststoff‘. Die internationale Veranstaltungsreihe soll voraussichtlich an mehr als 40 Orten stattfinden. Den Start macht am 29. Januar der Firmenhauptsitz des Unternehmens in Braunschweig. Ziel ist es, Spezialisten aus der Kunststoffbranche und der optischen Messtechnik zusammenzubringen, um Wissen und Erfahrungen austauschen zu können.

www.gom.com

Anzeige

Die Deutsche Arbeitsgemeinschaft für Mustererkennung blick auf eine erfolgreiche ‚German Conference on Pattern Recognition‘ zurück. Die bereits 40. Auflage der Konferenz fand vom 09. bis 12. Oktober an der Universität Stuttgart statt. Mehr als 200 Teilnehmer tauschten sich über die wichtigsten Neuerungen aus der Bildverarbeitung und Mustererkennung aus. Dabei standen insbesondere die Trendthemen Künstliche Intelligenz und Maschinelles Lernen im Fokus.

gcprvmv2018.vis.uni-stuttgart.de

Anzeige

Framos hat sein globales Partner-Netzwerk um Rhonda Software erweitert, um sein modular aufgebautes Embedded-Vision-Angebot zu vervollständigen.

rhondasoftware.com

Anzeige
Anzeige
Anzeige
Anzeige
Anzeige
Anzeige
Anzeige