Locality defeats the curse of dimensionality in convolutional teacher-student scenarios
Related publications (37)
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.
We propose a gaze-based indicator of students’ attention in a MOOC video lecture. We report the results from an eye-tracking study during a MOOC lecture. We define the gaze- based indicator of students’ attention as “with-me-ness”. This answers a question ...
Sigmoid-like activation functions implemented in analog hardware differ in various ways from the standard sigmoidal function as they are asymmetric, truncated, and have a non-standard gain. It is demonstrated how one can adapt the backpropagation learning ...
Although we were required to lecture to large groups of over 170 students, the traditional lecture clashed with our commitment to teach in a way that was student-centred, relational and socially and politically transformative. In this context, and using an ...
The backpropagation algorithm is widely used for training multilayer neural networks. In this publication the steepness of its activation functions is investigated. In specific, it is discussed that changing the steepness of the activation function is equi ...
The goal of the scene labeling task is to assign a class label to each pixel in an image. To ensure a good visual coherence and a high class accu- racy, it is essential for a model to capture long range (pixel) label dependencies in images. In a feed-forwa ...
Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to. To ensure a good visual coherence and a high class accuracy, it is essential for a scene parser to capture image long range depende ...
This study proposes a new technique for real-time building energy modelling and event detection using kernel regression. We show that this technique can exceed the performance of conventional neural network algorithms, and do so by a large margin when the ...