Mei to Use AI to Improve Relationships

The application will help people fill in the gaps in communication
07 August 2018   975

Es Lee, a graduate of the computer science department at Harvard University, founded the Mei start-up. The application will help people fill in the gaps in communication, giving advice on how to respond in various situations. This is reported by Venture Beat.

Mei processes messages using algorithms that take into account the response time, laconicity, word selection and other factors. Based on these data, the application builds a psychological portrait of the interlocutor. Lee argues that algorithms can determine the age of the interlocutor only on the emoticons used. If you add text to it, the application will understand what kind of relationship between people and determine their strength. 

One of the difficulties of maintaining relationships through text is that it’s [possible] to come across as crass or rude — even when that was never the intention. Emotion is lost in text messages. It’s a different form of body language that people aren’t quite attuned to detecting yet.

Es Lee

Creator, Mei

In practice, AI calculates the percentage of compatibility, taking into account 5 personality factors: openness, goodwill, conscientiousness, emotionality and extraversion. At the same time, he additionally breaks each of them into sub-points (original, stubborn, polite, etc.), and also identifies features that most closely match the two interlocutors (for example, pride and seriousness).

Mei Screen
Mei Screen

Mei has been trained on millions of messages from more than 100,000 application users, data from two universities and team development team correspondence. The messenger uses double encryption of messages, and they can be deleted at any time, regardless of whether they were read or not. There are instant messages that are deleted as soon as they are sent or read. According to the developers, the application is developed thanks to the data received from users.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   674

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.