École Normale Supérieure

About: École Normale Supérieure is a other organization based out in Paris, Île-de-France, France. It is known for research contribution in the topics: Population & Catalysis. The organization has 68439 authors who have published 99414 publications receiving 3092008 citations.

Learning Convolutional Feature Hierarchies for Visual Recognition

Abstract: We propose an unsupervised method for learning multi-stage hierarchies of sparse convolutional features. While sparse coding has become an increasingly popular method for learning visual features, it is most often trained at the patch level. Applying the resulting filters convolutionally results in highly redundant codes because overlapping patches are encoded in isolation. By training convolutionally over large image windows, our method reduces the redudancy between feature vectors at neighboring locations and improves the efficiency of the overall representation. In addition to a linear decoder that reconstructs the image from sparse features, our method trains an efficient feed-forward encoder that predicts quasi-sparse features from the input. While patch-based training rarely produces anything but oriented edge detectors, we show that convolutional training produces highly diverse filters, including center-surround filters, corner detectors, cross detectors, and oriented grating detectors. We show that using these filters in multistage convolutional network architecture improves performance on a number of visual recognition and detection tasks.

What phonological deficit

Abstract: We review a series of experiments aimed at understanding the nature of the phonological deficit in developmental dyslexia. These experiments investigate input and output phonological representations, phonological grammar, foreign speech perception and production, and unconscious speech processing and lexical access. Our results converge on the observation that the phonological representations of people with dyslexia may be intact, and that the phonological deficit surfaces only as a function of certain task requirements, notably short-term memory, conscious awareness, and time constraints. In an attempt to reformulate those task requirements more economically, we propose that individuals with dyslexia have a deficit in access to phonological representations. We discuss the explanatory power of this concept and we speculate that a similar notion might also adequately describe the nature of other associated cognitive deficits when present.

High transconductance organic electrochemical transistors.

Abstract: The development of transistors with high gain is essential for applications ranging from switching elements and drivers to transducers for chemical and biological sensing. Organic transistors have become well-established based on their distinct advantages, including ease of fabrication, synthetic freedom for chemical functionalization, and the ability to take on unique form factors. These devices, however, are largely viewed as belonging to the low-end of the performance spectrum. Here we present organic electrochemical transistors with a transconductance in the mS range, outperforming transistors from both traditional and emerging semiconductors. The transconductance of these devices remains fairly constant from DC up to a frequency of the order of 1 kHz, a value determined by the process of ion transport between the electrolyte and the channel. These devices, which continue to work even after being crumpled, are predicted to be highly relevant as transducers in biosensing applications.