Mei to Use AI to Improve Relationships

The application will help people fill in the gaps in communication
07 August 2018   622

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.

Facebook to Release PyTorch 1.0

This release added support for large cloud platforms, a C ++ interface, a set of JIT compilers
10 December 2018   106

Facebook has released a stable version of the library for machine learning PyTorch 1.0. This iteration added support for large cloud platforms, a C ++ interface, a set of JIT compilers, and various improvements.

The stable version received a set of JIT compilers that eliminate the dependence of the code on the Python interpreter. The model code is transformed into Torch Script - a superstructure over Python. Keeping the opportunity to work with the model in the Python environment, the user can download it to other projects not related to this language. So, the PyTorch developers state that the code processed in this way can be used in the C ++ API.

The torch.distributed package and the torch.nn.parallel.DistributedDataParallel module are completely redesigned. torch.distributed now has better performance and works asynchronously with the Gloo, NCCL and MPI libraries.

The developers added a C ++ wrapper to PyTorch 1.0. It contains analogs of Python interface components, such astorch.nn,torch.optim, torch.data. According to the creators, the new interface should provide high performance for C ++ applications. True, the C ++ API is still experimental, but it can be used in projects now.

To improve the efficiency of working with PyTorch 1.0, a Torch Hub repository has been created, which stores pre-trained models of neural networks. You can publish your own development using the hubconf.py file, after which the model will be available for download by any user via the torch.hub.load API.

Support for C extensions and the module torch.utils.trainer were removed from the library.

Facebook released the preliminary version of PyTorch 1.0 at the beginning of October 2018, and in two months the developers brought the framework to a stable state.