Thank you Lodz University of Technology and Polish Alliance for the Development of Artificial Intelligence (https://pp-rai.pl/) for organizing the 4th Polish Conference on Artificial Intelligence. The last three days were filled with engaging presentations and inspiring discussions. We shared recent results of our "Bipolar Disorder prediction with sensor-based semi-supervised learning" (BIPOLAR) project. A PhD researcher Kamil Kmita presented a poster about neural network with learnable activations for one-sided control limits where we experimented with boosted sigmoid to approximate threshold functions (joint work with prof. Olgierd Hryniewicz). Our second poster presentation was spearheaded by Filip Wichrowski (who has just started his PhD). Filip discussed the results of our collaboration with Víctor Elvira related to Bipolar Disorder monitoring with speech signal using Hidden Markov Models (HMM). In a nutshell, we’ve observed that HMMs provide more consistent and accurate predictions by making effective use of the hidden states structure. Great to (re)connect with so many colleagues and already looking forward to the next edition of the Conference in Warsaw!
BACK