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 this work and the supporting Part II [1], we examine the performance of stochastic sub-gradient learning strategies under weaker conditions than usually considered in the literature. The new conditions are shown to be automatically satisfied by several ...
Bounding the generalization error of learning algorithms has a long history, which yet falls short in explaining various generalization successes including those of deep learning. Two important difficulties are (i) exploiting the dependencies between the h ...
Automatic Speech Recognition (ASR) can introduce higher levels of automation into Air Traffic Control (ATC), where spoken language is still the predominant form of communication. While ATC uses standard phraseology and a limited vocabulary, we need to adap ...
This report presents key interdisciplinary insights from IRGC’s expert workshop on the governance of decision-making algorithms, with particular focus on automated decisions based on learning algorithms (DMLAs). It highlights, among others, the need to imp ...
Our brain continuously self-organizes to construct and maintain an internal representation of the world based on the information arriving through sensory stimuli. Remarkably, cortical areas related to different sensory modalities appear to share the same f ...
The problem of acquiring multiple tasks from demonstration is typi- cally divided in two sequential processes: (1) the segmentation or identification of different subgoals/subtasks and (2) a separate learning process that parameterizes a control policy for ...
Real behavior of existing structures is usually associated with large uncertainty that is often covered by the use of conservative models and code practices for the evaluation of remaining fatigue lives. In order to make better decisions related to retrofi ...
Several techniques have been recently proposed to adapt Big-Data streaming applications to existing many core platforms. Among these techniques, online reinforcement learning methods have been proposed that learn how to adapt at run-time the throughput and ...
Institute of Electrical and Electronics Engineers2016
Automatic Speech Recognition (ASR) can introduce higher levels of automation into Air Traffic Control (ATC), where spoken language is still the predominant form of communication. While ATC uses standard phraseology and a limited vocabulary, we need to adap ...
Reinforcement learning is a type of supervised learning, where reward is sparse and delayed. For example in chess, a series of moves is made until a sparse reward (win, loss) is issued, which makes it impossible to evaluate the value of a single move. Stil ...