AI Brainscans

Gepostet vor 2 Monaten, 27 Tagen in #Design #Tech #AI #AlgoCulture #DataVisualization

Share: Twitter Facebook Mail

Graphcore aus Bristol visualisieren künstliche Intelligenzen und Neural Networks: Inside an AI 'brain' - What does machine learning look like? Im Bild oben sieht man AlexNet, ein Deep Neural Network, das 2012 einen Preis für den Durchbruch bei Bilderkennung gewann. (via NewAesthetics)

One aspect all recent machine learning frameworks have in common - TensorFlow, MxNet, Caffe, Theano, Torch and others - is that they use the concept of a computational graph as a powerful abstraction. A graph is simply the best way to describe the models you create in a machine learning system. These computational graphs are made up of vertices (think neurons) for the compute elements, connected by edges (think synapses), which describe the communication paths between vertices.

Unlike a scalar CPU or a vector GPU, the Graphcore Intelligent Processing Unit (IPU) is a graph processor. A computer that is designed to manipulate graphs is the ideal target for the computational graph models that are created by machine learning frameworks.

We’ve found one of the easiest ways to describe this is to visualize it. Our software team has developed an amazing set of images of the computational graphs mapped to our IPU. These images are striking because they look so much like a human brain scan once the complexity of the connections is revealed – and they are incredibly beautiful too.

Mehr bei Wired: 'AI brain scans' reveal what happens inside machine learning.

full training graph for Microsoft Research ResNet-34 architecture hosted on Graphcore's IPU from December 2016. The image is coloured to highlight the density of computation resulting the glowing centre in the convolutional layers of the graph

The ResNet architecture is used for building deep neural networks for computer vision and image recognition. The image shown here is the forward (inference) pass of the ResNet 50 layer network used to classify images after being trained using the Graphcore neural network graph library

Resnet 50: deep neural network, A graph processor such as the IPU is designed specifically for building and executing computational graph networks for deep learning and machine learning models of all types. What’s more, the whole model can be hosted on an IPU. This means IPU systems train machine learning models much faster than, and deploy them for inference or prediction much more efficiently than other processors which were simply not designed for this new and important workload. Machine learning is the future of computing and a graph processor like the IPU is the architecture that will carry this next wave of computing forward.

The AlexNet image classification training architecture from November 2016. The vertices in the final three layers of AlexNet are coloured while the rest of the graph is in black and white

An image of the ResNet-34 forward pass used for image recognition. The graph visually shows where multiple images are sent through the network in parallel. This is known as batching

Neural Network sorts Skate Decks

David De Vigne hat ein Neural Network auf seine Sammlung von Skatedecks trainiert und hat sie damit nach visuellen Merkmalen…

How Computer Vision Is Finally Taking Off

Nat and Friends: „Computer vision is fascinating to me because a) it sounds intriguing and b) it’s a part of…

Deep Dreaming an Art Archive

Tolle Installation des türkischen Künstlers Refik Anadol, der eine künstliche Intelligenz und ihr Machine Learning auf das Archiv des SALT…

Neulich in Darmstadt: Das Geile Neue Internet – Potential of (visible) Infinite Idea Space

[update] Hier ein Livestream auf Facebook. Hier der Vortrag auf Youtube. Wer einem sehr nervösen Typen auf einer Bühne beim…

Smile-Filtering a Face until there is no Face left to smile-filter

Gene Kogan: „just in case you were wondering, this is what happens when you repeatedly run FaceApp’s smile filter until…

Neural Network dreams your Dreams

Wissenschaftler können bereits seit Jahren Bilder aus Gehirnscans extrahieren, also: Tatsächlich ein Abbild davon schaffen, was wir sehen. Die Resultate…

Neural Network dreams of riding a Train

Tolle Arbeit von Damien Henry: Ein Neural Network, ein sogenannter „prediction algorithm“, der Frames eines Videos „errät“, ausgehend vom jeweils…

4 AI-Obamas learn Algo-Lipsynch from Audio

Seit ich über die neuen Möglichkeiten von Machine Learning bezüglich Computer Vision und der Generation von Bildern schreibe, vor allem…

Daddy Cthulhu Cumshot: Weird Algo-Poetry from repetitive Cut'n'Paste-Autocomplete

Das LanguageLog hat die „psychedellic“ AI-„Dreaming of“-Technik auf Google Translate angewandt und dort regelmäßige Sprach/Zeichen-Muster („Iä! Iä! Iä! Iä! Iä!…

Neural Networks for Character Control

Daniel Holden, Taku Komura und Jun Saito haben ein Neural Network auf Character-Animationen trainiert, mit dem Figuren in Games und…

Predictive Policing for Banksters

Schönes Ding von Sam Lavigne, Predictive Policing für Wirtschaftskriminalität im Finanzsektor, 'ne Robocop-App für Bankster. White Collar Crime Risk Zones…