Robust Generalization via $\alpha$-Mutual Information
Graph Chatbot
Chat with Graph Search
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.
In the meeting case scenario, audio is often recorded using Multiple Distance Microphones (MDM) in a non-intrusive manner. Typically a beamforming is performed in order to obtain a single enhanced signal out of the multiple channels. This paper investigate ...
We present a method for multimodal fusion based on the estimated reliability of each individual modality. Our method uses an information theoretic measure, the entropy derived from the state probability distribution for each stream, as an estimate of relia ...
Here, I review facts that are most probably known, namely that the information gain criterion used to drive experimental design in a linear-Gaussian model is submodular, so that a well-known approximation guarantee holds for the sequential greedy algorithm ...
Attentional capture is often thought to be automatic and not modulable. For example, visual search experiments showed that salient distractor singletons strongly capture attention even when they had to be ignored by the observers. Recently, however, it was ...
We introduce the notion of permissiveness in transactional memories (TM). Intuitively, a TM is permissive if it never aborts a transaction when it need not. More specifically, a TM is permissive with respect to a safety property p if the TM accepts every ...
This paper presents a first approach to dynamic frequency-based transit assignment. As such the model aims to close the gap between schedule-based and frequency-based models. Frequency-based approaches have some advantages compared to schedule-based models ...
In this paper, two fixed per-information symbol complexity lossless source coding algorithms are modified for estimation and incremental LT decoding over piecewise stationary memoryless channels (PSMC's) with a bounded number of abrupt changes in channel s ...
Understanding the guiding principles of sensory coding strategies is a main goal in computational neuroscience. Among others, the principles of predictive coding and slowness appear to capture aspects of sensory processing. Predictive coding postulates tha ...
A speaker diarization system based on an information theoretic framework is described. The problem is formulated according to the {\em Information Bottleneck} (IB) principle. Unlike other approaches where the distance between speaker segments is arbitraril ...
We investigate the invariance of posterior features estimated using MLP trained on auxiliary corpus towards different data condition and different distance measures for matching posterior features in the context of template-based ASR. Through ASR studies o ...
