background preloader

Deep learning

Facebook Twitter

What is Deep Learning? Deep Learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks. If you are just starting out in the field of deep learning or you had some experience with neural networks some time ago, you may be confused. I know I was confused initially and so were many of my colleagues and friends who learned and used neural networks in the 1990s and early 2000s.

The leaders and experts in the field have ideas of what deep learning is and these specific and nuanced perspectives shed a lot of light on what deep learning is all about. In this post, you will discover exactly what deep learning is by hearing from a range of experts and leaders in the field. Let’s dive in. What is Deep Learning? Deep Learning is Large Neural Networks He has spoken and written a lot about what deep learning is and is a good place to start. Later his comments became more nuanced. He provides a nice cartoon of this in his slides: Summary. Deep Learning Will Radically Change the Ways We Interact with Technology. Even though heat and sound are both forms of energy, when you were a kid, you probably didn’t need to be told not to speak in thermal convection. And each time your children come across a stray animal, they likely don’t have to self-consciously rehearse a subroutine of zoological attributes to decide whether it’s a cat or a dog.

Human beings come pre-loaded with the cognitive gear to simply perceive these distinctions. The differences appear so obvious, and knowing the differences comes so naturally to us, that we refer to it as common sense. Computers, in contrast, need step-by-step handholding—in the form of deterministic algorithms—to render even the most basic of judgments. Despite decades of unbroken gains in speed and processing capacity, machines can’t do what the average toddler does without even trying. That is—until now. This is only the beginning. Deep Learning So how does deep learning work? For a neural network to be useful, though, it requires training. Deep Learning OS 1.0. Cette intelligence artificielle s'inspire des humains pour apprendre beaucoup plus vite. En poursuivant votre navigation sur ce site, vous acceptez nos CGU et l'utilisation de cookies afin de réaliser des statistiques d'audiences et vous proposer une navigation optimale, la possibilité de partager des contenus sur des réseaux sociaux ainsi que des services et offres adaptés à vos centres d'intérêts.

Pour en savoir plus et paramétrer les cookies... Accueil PierreFONTAINE Journaliste Inscrivez-vous gratuitement à laNewsletter Actualités Une start-up vient de dévoiler une nouvelle méthode d’apprentissage pour les IA qui pourrait bouleverser la donne. Sans le deep learning, la révolution actuelle de l’intelligence artificielle n’existerait sans doute pas. De son côté et schématiquement, l’humain apprend en établissant une « idée » de ce qu’est un chat. Gagner du temps et nécessiter moins de données… Le résultat est à la fois un gain de temps et un besoin moindre en données pendant l’apprentissage. . … pour utiliser moins de puissance De multiples cas d'usages ? Pierre FONTAINE Tweeter. Google’s new machine learning API recognizes objects in videos – TechCrunch. At its Cloud Next conference in San Francisco, Google today announced the launch of a new machine learning API for automatically recognizing objects in videos and making them searchable.

The new Video Intelligence API will allow developers to build applications that can automatically extract entities from a video. Until now, most similar image recognition APIs available in the cloud only focused on doing this for still images, but with the help of this new API, developers will be able to build applications that let users search and discover information in videos. That means you can search for “dog” or “flower,” for example. Besides extracting metadata, the API allows you to tag scene changes in a video. Those videos have to be stored in Google’s cloud storage service. You can see a demo of how this works here. As Google’s Fei-Fei Li, its chief scientist of AI and Machine Learning at Google Cloud, noted in today’s keynote, the world of pixels goes beyond images.