Search

Rapid progress in technologies such as calcium imaging and electrophysiology has seen a dramatic increase in the size and extent of neural recordings. Even so, interpretation of this data requires considerable knowledge about the nature of the representation and often depends on manual operations. Decoding provides a means to infer the information content of such recordings but typically requires highly processed data and prior knowledge of the encoding scheme. Here, we developed a deep-learning framework able to decode sensory and behavioral variables directly from wide-band neural data. The network requires little user input and generalizes across stimuli, behaviors, brain regions, and recording techniques. Once trained, it can be analyzed to determine elements of the neural code that are informative about a given variable. We validated this approach using electrophysiological and calcium-imaging data from rodent auditory cortex and hippocampus as well as human electrocorticography (ECoG) data. We show successful decoding of finger movement, auditory stimuli, and spatial behaviors – including a novel representation of head direction - from raw neural activity.

Rapid progress in technologies such as calcium imaging and electrophysiology has seen a dramatic increase in the size and extent of neural recordings. Even so, interpretation of this data often depends on manual operations and requires considerable knowledge about the nature of the representation. Decoding provides a means to infer the information content of such recordings but typically requires highly processed data and prior knowledge of the encoding scheme. Here, we developed a deep-learning-framework able to decode sensory and behavioural variables directly from wide-band neural data. The network requires little user input and generalizes across stimuli, behaviours, brain regions, and recording techniques. Once trained, it can be analysed to determine elements of the neural code that are informative about a given variable. We validated this approach using data from rodent auditory cortex and hippocampus, identifying a novel representation of head direction encoded by putative CA1 interneurons.

BACKGROUND: In industrialized countries, typhoid fever occurs mainly in returned travelers. To determine the need for preventive strategies, eg, for vaccination, continuous monitoring is needed to assess where the risk for travelers is highest. METHODS: To investigate where the risk for travelers to acquire typhoid fever is highest, 208 patients with typhoid fever and recent travel were matched with travelers' statistics collected by the Swiss Federal Office of Statistics. RESULTS: At the beginning of the study period, up to 30 infections with Salmonella typhi were recorded per year in Switzerland. Since 2001, less than 15 confirmed cases per year occurred. A majority of the 208 (88.5%) typhoid cases were associated with recent travel. Countries with highest risk were Pakistan (24 per 100,000), Cambodia (20 per 100,000), Nepal (14 per 100,000), India (12 per 100,000), and Sri Lanka (9 per 100,000). CONCLUSIONS: We found that over a 12-year period (1993-2004), the travel-associated risk of typhoid fever is highest for destinations in the Indian subcontinent. All other regions showed a decline, most markedly in southern Europe. Our results suggest that typhoid fever vaccination should be recommended for all travelers to countries in South Asia. Otherwise, vaccination of tourists to frequently visited low- and intermediate-risk areas is not necessary, unless there are behavioral risk factors.

In this paper a novel approach to fuzzy support vector machines (SVM) in multi-class classification problems is presented. The proposed algorithm has the property to benefit from fuzzy labeled data in the training phase and can determine fuzzy memberships for input data. The algorithm can be considered as an extension of the traditional multi-class SVM for crisp labeled data, and it also extents the fuzzy SVM approach for fuzzy labeled training data in the two-class classification setting. Its behavior is demonstrated on three benchmark data sets, the achieved results motivate the inclusion of fuzzy labeled data into the training set for various tasks in pattern recognition and machine learning, such as the design of aggregation rules in multiple classifier systems, or in partially supervised learning.