Recently, a PhD researcher, Daniele Grattarola built a framework known as Spektral for mapping relational representation learning which is built in Python and is based on the Keras API. Spektral contains a comprehensive set of tools to build graph neural networks as well as implement some of the popular layers for graph Deep Learning. Spektral is built with semi-supervised deep learning methods for graph data, Graph Neural Network (GNN). According to this paper, the idea of GNN is simple: to encode structural information of the graph, each node v_i can be represented by a low-dimensional state vector s_i, 1 i N. The categorisation of deep learning methods on the graph is shown below The core GNN modules of Spektral are mainly based on Keras and it works with all the different backends offered by Keras in order to promptly start experimenting with the Relational Representation Learning (RRL) which consists of developing models that are able to deal with graphs natively without having to deal with the distracting low-level details. The accessory modules of Spectral are built in Numpy/Scipy and for which everything should work at the speed of almost-C-like and without compatibility issues.

If you're a deep learning enthusiast you're probably already familiar with some of the basic mathematical primitives that have been driving the impressive capabilities of what we call deep neural networks. Although we like to think of a basic artificial neural network as some nodes with some weighted connections, it's more efficient computationally to think of neural networks as matrix multiplication all the way down. We might draw a cartoon of an artificial neural network like the figure below, with information traveling in from left to right from inputs to outputs (ignoring recurrent networks for now). This type of neural network is a feed-forward multilayer perceptron (MLP). If we want a computer to compute the forward pass for this model, it's going to use a string of matrix multiplies and some sort of non-linearity (here represented by the Greek letter sigma) in the hidden layer: MLPs are well-suited for data that can be naturally shaped as 1D vectors.

In this paper we present Spektral, an open-source Python library for building graph neural networks with TensorFlow and the Keras application programming interface. Spektral implements a large set of methods for deep learning on graphs, including message-passing and pooling operators, as well as utilities for processing graphs and loading popular benchmark datasets. The purpose of this library is to provide the essential building blocks for creating graph neural networks, focusing on the guiding principles of user-friendliness and quick prototyping on which Keras is based. Spektral is, therefore, suitable for absolute beginners and expert deep learning practitioners alike. In this work, we present an overview of Spektral's features and report the performance of the methods implemented by the library in scenarios of node classification, graph classification, and graph regression.

Recently, a PhD researcher, Daniele Grattarola built a framework known as Spektral for mapping relational representation learning which is built in Python and is based on the Keras API. Spektral contains a comprehensive set of tools to build graph neural networks as well as implement some of the popular layers for graph Deep Learning. Spektral is built with semi-supervised deep learning methods for graph data, Graph Neural Network (GNN). According to this paper, the idea of GNN is simple: to encode structural information of the graph, each node v_i can be represented by a low-dimensional state vector s_i, 1 i N. The categorisation of deep learning methods on the graph is shown below The core GNN modules of Spektral are mainly based on Keras and it works with all the different backends offered by Keras in order to promptly start experimenting with the Relational Representation Learning (RRL) which consists of developing models that are able to deal with graphs natively without having to deal with the distracting low-level details. The accessory modules of Spectral are built in Numpy/Scipy and for which everything should work at the speed of almost-C-like and without compatibility issues.

Apple has quietly bought Spektral, a Danish machine learning startup that specializes in real-time green screen technology. The $30 million deal actually happened last year, but it was reported today by Danish newspaper Børsen. Apple has been focusing more and more on its AR capabilities lately, and this latest acquisition may be meant to boost the iPhone's AR features for Memoji or FaceTime or as a part of its plans for an augmented reality headset, which Bloomberg reported may be coming in 2020. Spektral, which previously went by the name CloudCutout, uses machine learning and computer vision techniques to "cut out" people from video backgrounds in real time on smartphones. "Combining deep neural networks and spectral graph theory with the computing power of modern GPUs, our engine can process images and video from the camera in real-time (60 fps) directly on the device," the company explained on its website.

Apple has doubled down on AR by acquiring Danish machine learning company Spektral, whose software erases backgrounds from videos instantly. The purchase remained quiet until Danish newspaper Børsen broke the news today. Fortune notes that the deal closed in December 2017 for a cool $30 million. Apple is no stranger to under-the-radar buyouts, and the Spektral acquisition doesn't come as a surprise given the Danish startup's expertise. Spektral, formerly named'CloudCutout,' uses spectral graph theory and deep neural networks to create what is essentially green screen video editing, but in real time.