This study evaluates the recently proposed Document Attention Network (DAN) for extracting key-value information from Uruguayan birth certificates, handwritten in Spanish. We investigate two annotation strategies for automatically transcribing handwritten documents, fine-tuning DAN with minimal training data and annotation effort. Experiments were conducted on two datasets containing the same images (201 scans of birth certificates written by more than 15 different writers) but with different annotation methods. Our findings indicate that normalized annotation is more effective for fields that can be standardized, such as dates and places of birth, whereas diplomatic annotation performs much better for fields containing names and surnames, which can not be standardized.

Will we be able to copy the human mind? Elon Musk recently presented the latest efforts of Neuralink, a company that he founded in 2016 and which has grand aspirations of developing an implantable Brain-Machine Interface or BMI (for my prior coverage on Neuralink see the link here, for my analysis of the potential future of BMI, see the link here). Despite some interesting show-and-tell, including pigs involved in the ongoing experiments, much of the discussion was rather speculative and spurred some to later ask where's the beef, likening the event as little more than neuroscience theatre and noting some internal angst about the way that the engineering and science is being conducted. In any case, the Q&A led to some fascinating postulations about the possibilities of being someday able to copy the human mind. Let's use that as a means to consider how copying the human mind can be related to AI, along with then using AI-based true self-driving cars as an example for exploring the mind-copying aspects. First of all, if you make a copy of something, is it the same as the original?

The Infant Mortality Rate (IMR) is the number of infants per 1000 that do not survive until their first birthday. It is an important metric providing information about infant health but it also measures the society's general health status. Despite the high level of prosperity in the U.S.A., the country's IMR is higher than that of many other developed countries. Additionally, the U.S.A. exhibits persistent inequalities in the IMR across different racial and ethnic groups. In this paper, we study the infant mortality prediction using features extracted from birth certificates. We are interested in training classification models to decide whether an infant will survive or not. We focus on exploring and understanding the importance of features in subsets of the population; we compare models trained for individual races to general models. Our evaluation shows that our methodology outperforms standard classification methods used by epidemiology researchers.