A man who spent 41 years on death row in the US after being convicted of killing a woman has been released on bail after prosecutors said newly analysed DNA evidence did not link him to the crime. Douglas Stewart Carter, who is now 71, was jailed for the killing of Eva Olesen in Utah in 1985. He was sentenced to death but always maintained his innocence, stating that a signed confession was coerced. The state Supreme Court ordered a new trial last year, citing misconduct by investigators, and a judge bailed Carter on Monday despite objections from the victim's family. He is required to wear a GPS monitor while on bail.

Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.

The paper describes aHUGIN, a tool for creating adaptive systems. aHUGIN is an extension of the HUGIN shell, and is based on the methods reported by Spiegelhalter and Lauritzen (1990a). The adaptive systems resulting from aHUGIN are able to adjust the C011ditional probabilities in the model. A short analysis of the adaptation task is given and the features of aHUGIN are described. Finally a session with experiments is reported and the results are discussed.