AI Brainscans

Gepostet vor 4 Monaten, 21 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

Cellular Automata Cube Conways Game of Life als 3D-Spielzeug mit Cubes und Spheres und Schnickschnack als Evolution-Nullpunkt, von wo aus die ganzen…

Neural Network-Faces synched to Music

„My first attempt to map a song made by @kamptweets onto GAN generated proto-faces.“ Bohemian Rhapsody next. The Three Nightingans.…

AI-Animations with human Sounds

Google vor ein paar Tagen so: „Yay, wir haben hier 'ne neue AI-based Animation-Tech, hooray!“ (Paper) Hayayo Miyazaki über AI-based…

Data-Visualized Skateboarding

Paul Ferragut bestückt sein Skateboard mit Sensoren und bastelt damit 3D-Prints aus Sk8-Tricks. Funktioniert eher rudimentär, dafür aber DIY mit…

Visual AI-Spaces Auto-Pilot

Ich habe schon ein paar mal über Mario Klingemanns Arbeiten hier gebloggt, derzeit jagt er Neural Networks durch Feedback-Loops und…

Synthesizing Obama from Audio

Im Mai bloggte ich über ein damals noch nicht veröffentlichtes Paper zur SigGraph2017, in dem sie eine Methode für generative…

Generative Pearls

Cool fractal and generative art by Julien Leonard. I dig his explanation from his about-page: „I create algorithms that connect…


Mario Klingemann does some weird shit again with CycleGAN Feedback Loops (Neural Networks feeding their results back to each other).…

Floral Algorithm dreams of Dinosaurs

Chris Rodley (Twitter) hat seinen Styletransfer-Bot mit Blumen gefüttert und auf Dinosaurier angesetzt.

3D-Visualized Typography-Ideaspace

Ich habe schon einige AI-Visualisierungen von Fonts gesehen, also sortierte Abbildungen des visuellen Idea-Space der Zeichensätze (also genau wie Skateboards…

Map of Geocities: The Deleted City 3.0

Tolle Visualisierung der ollen Geocities-Websites auf einer Karte. Das Teil lädt bei mir grade eher langsam und dort wo offenbar…