Modeling language and cognition with deep unsupervised learning: a tutorial overview.

Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this article we discuss the theoretical foundations of this approach and we review key issues related to training, testing and analysis of deep networks for modeling language and cognitive processing. The classic letter and word perception problem of McClelland and Rumelhart (1981) is used as a tutorial example to illustrate how structured and abstract representations may emerge from deep generative learning. We argue that the focus on deep architectures and generative (rather than discriminative) learning represents a crucial step forward for the connectionist modeling enterprise, because it offers a more plausible model of cortical learning as well as a way to bridge the gap between emergentist connectionist models and structured Bayesian models of cognition.

Perinatal asphyxia affects rat auditory processing: implications for auditory perceptual impairments in neurodevelopmental disorders.

Perinatal asphyxia, a naturally and commonly occurring risk factor in birthing, represents one of the major causes of neonatal encephalopathy with long term consequences for infants. Here, degraded spectral and temporal responses to sounds were recorded from neurons in the primary auditory cortex (A1) of adult rats exposed to asphyxia at birth. Response onset latencies and durations were increased. Response amplitudes were reduced. Tuning curves were broader. Degraded successive-stimulus masking inhibitory mechanisms were associated with a reduced capability of neurons to follow higher-rate repetitive stimuli. The architecture of peripheral inner ear sensory epithelium was preserved, suggesting that recorded abnormalities can be of central origin. Some implications of these findings for the genesis of language perception deficits or for impaired language expression recorded in developmental disorders, such as autism spectrum disorders, contributed to by perinatal asphyxia, are discussed.