Amazon Technologies, Inc.

Maksim Lapin

Leo Parker Dirac

Rui Chen

Loris Bazzani

Gerard Gjonej

Felix Hieber

Aleix Margarit Martinez

Anqi Liang

Tobias Domhan

Bradley Scott Bowman

Techniques are generally described for an artificial intelligence based interior designer system. In various examples, an image comprising a plurality of items arranged together in a room may be received. A visual representation and a positional representation of each item represented in the image may be determined. An output embedding may be generated based at least in part on the visual representation and the positional representation of each item represented in the image. At least one output item may be determined based at least in part on the output embedding. An image of the at least one output item may be displayed in association with the image comprising the plurality of items arranged together in the room.

Artificial intelligence interior design system

Techniques for evaluating an output of a machine learning model and using the evaluation to retrain the machine learning model are described. For example, a data set that is output from a layer of the machine learning model is reduced to a 2-D or 3-D representation that is suitable for viewing. A user views the reduced data set in a viewing environment such as virtual reality or augmented reality. The user makes changes using that viewing environment. The changes are then used to retrain the machine learning model.

Virtual/augmented reality data evaluation

Techniques are generally described for automatic scoring of alt-text for image data. In various examples, first image data and first text data describing the first image data may be received. A feature representation of the first image data may be determined using an encoder machine learning model. A hidden state representation may be determined using a decoder machine learning model based on the feature representation and a first word of the first text data. In some examples, a first score may be determined using the hidden state representation. The first score may include an indication of a descriptive capability of the first text data with respect to the first image data.

Machine learning system to score alt-text in image data

Growing community of inventors

Berlin, Germany

Maksim Lapin