The Information plane can be used to gain insight and theoretical understanding of neural networks.

Image:

Opening the black box of AI

Although Deep Neural Networks (DNNs) are at the core of most state–of–the art systems in computer vision, the theoretical understanding and explainability possibilities of such networks is still not at a satisfactory level.

To a large degree, our user partner’s applications involve imaging the unseen – the inside of the human body, the sea, and the surface of the earth seen from space independent of daylight and weather conditions. Impact of innovative technology for users depends on trust. A limitation of deep learning models is that there is no generally accepted solution for how to open the “black-box” of the deep network to provide explainable decisions which can be relied on to be trustworthy.

Visual Intelligence aims at developing deep learning models with built-in robustness to data domain shift that also offers a high-level explainability.

Video

Further reading

New algorithms for vessel and object detection
January 19, 2021
Visual Intelligence collaborates with KSAT to improve existing, and develop new algorithms, for vessel detection and object recognition.
New methods for automatic change detection in aerial images
January 19, 2021
A collaboration with Terratec to develop deep learning methods to automatically detect changes when updating an existing map database.
Modelling continuity in seismic data
January 19, 2021
Visual intelligence is collaborating with Equinor to develop models that can exploit seismicdata and model the continuity of the subsurface.