Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
Assessing pattern printability in new large layouts faces important challenges of runtime and false detection. Lithographic simulation tools and classification techniques do not scale well. We propose a fast pattern detection method by learning an overcomp ...
Automatic speech recognition (ASR) systems, through use of the phoneme as an intermediary unit representation, split the problem of modeling the relationship between the written form, i.e., the text and the acoustic speech signal into two disjoint processe ...
Because of different designs, different text input devices have different error patterns. If we consider these aspects when designing an error correction mechanism, we can obtain significantly lower error rates. In this paper, we propose and evaluate a spe ...
In this paper, we consider learning dictionary models over a network of agents, where each agent is only in charge of a portion of the dictionary elements. This formulation is relevant in big data scenarios where multiple large dictionary models may be spr ...
Statistical speech recognition has been cast as a natural realization of the compressive sensing and sparse recovery. The compressed acoustic observations are sub-word posterior probabilities obtained from a deep neural network (DNN). Dictionary learning a ...
The Kamusi Project, a multilingual online dictionary website, has as one of its goals to document the lexicons of en-dangered and less-resourced languages (LRLs). Kamusi.org provides a unified platform and repository for this kind of data that is both simp ...
This paper looks at the challenges that the Kamusi Project faces for acquiring open lexical data for less-resourced languages (LRLs), of a range, depth, and quality that can be useful within Human Language Technology (HLT). These challenges include accessi ...
Sparse representations of images in well-designed dictionaries can be used for effective classification. Meanwhile, training data available in most realistic settings are likely to be exposed to geometric transformations, which poses a challenge for the de ...
Proteins are a ubiquitous and indispensable element for every living organism, from simple bacteria to mammals. Already in the simplest organisms, there exist some thousands of different protein species that take up a great variety of structures, and thus ...
In sparse signal representation, the choice of a dictionary often involves a tradeoff between two desirable properties – the ability to adapt to specific signal data and a fast implementation of the dictionary. To sparsely represent signals residing on wei ...
Institute of Electrical and Electronics Engineers2014