Do deep reinforcement learning agents model intentions?
Our latest paper shows that deep reinforcement learning agents seem to model intentions of other agents in a cooperative task. Also that trained agents tend to overfit to each other and do not...
View ArticleClik here to view.
Activations of deep convolutional neural networks are aligned with gamma band...
Our paper is out in Nature Communications Biology: https://www.nature.com/articles/s42003-018-0110-y! We had a cool dataset from 100 patients who looked at some pictures while wearing intracranial...
View ArticleClik here to view.
What neural networks actually do?
I often see people mystifying artificial neural networks, like they would think or reason. Actually they are doing simple curve fitting and I have used the following example with students to take the...
View ArticleClik here to view.
The use of embeddings in OpenAI Five
While there has been much discussion about OpenAI bot behavior and general meaning of the matches for AI community, there has been surprisingly little technical analysis of their training methods and...
View ArticleClik here to view.
Brain-Computer Interface Competition 2019 introduced at Robotex
Robotex International with support from Computational Neuroscience Lab, Institute of Computer Science of University of Tartu and ABB Estonia has introduced Mind Control competition that will take place...
View ArticleDirect information transfer rate optimisation for SSVEP-based Brain-Computer...
In this work, Anti Ingel has developed a classification method for steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI). Brain-computer interface is a direct communication...
View Article