Neural Network to Recognize Depression

In subsequent testing, artificial intelligence managed to recognize depression in 77% of cases
06 September 2018   890

Researchers from the Computational Science and Artificial Intelligence Laboratory (CSAIL) of the Massachusetts Institute of Technology (MIT) have developed a neural network that allows to determine the level of depression of a patient. Artificial intelligence is able to establish an oppressed psychological state, without relying on context and without asking specific questions. To obtain the test result, it is enough to record a patient interview in video or audio format.

By training the neural network, CSAIL scientists used 142 interview records from the Distress Analysis Interview Corpus, a compilation intended for the diagnosis of mental illness. Artificial intelligence analyzed speech of patients, revealing sound and text patterns. Patterns have become, including word-markers, such as "sad", "low", combined with long pauses and a monotonous voice. The oppressed condition of each patient was assessed on a scale from 0 to 27. Depression was considered to be a level of 15 and above.

In subsequent testing, artificial intelligence managed to recognize depression in 77% of cases. According to the developers, this result is one of the best among all available.

The new technology is considered as a tool that allows to simplify the work of the therapist and specify certain markers, which should be noted in the diagnosis.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   672

NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.

Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.

Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.

To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.