Learn More
The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are the most general conditions under which the partition function is tractable? The answer leads to a new kind of deep architecture, which we call sum-product networks (SPNs) and will present in this abstract.
Reasoning with both probabilistic and deterministic dependencies is important for many real-world problems, and in particular for the emerging field of statistical relational learning. However, probabilistic inference methods like MCMC or belief propagation tend to give poor results when deter-ministic or near-deterministic dependencies are present, and(More)
The senescence-accelerated mouse (SAM) is a murine model of accelerated senescence that was established using phenotypic selection. The SAMP series includes nine substrains, each of which exhibits characteristic disorders. SAMP8 is known to exhibit age-dependent learning and memory deficits. In our previous study, we reported that brains from 12-month-old(More)
Morphological segmentation breaks words into morphemes (the basic semantic units). It is a key component for natural language processing systems. Unsupervised morphological segmentation is attractive, because in every language there are virtually unlimited supplies of text, but very few labeled resources. However, most existing model-based systems for(More)
Mild cognitive impairment (MCI) is generally referred to the transitional zone between normal cognitive function and early dementia or clinically probable Alzheimer's disease (AD). Oxidative stress plays a significant role in AD and is increased in the superior/middle temporal gyri of MCI subjects. Because AD involves hippocampal-resident memory(More)
Knowledge extraction from online repositories such as PubMed holds the promise of dramatically speeding up biomedical research and drug design. After initially focusing on recognizing proteins and binary interactions, the community has recently shifted their attention to the more ambitious task of recognizing complex, nested event structures.(More)