Algorithms for Efficient and Robust Distributed Deep Learning
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.
The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset. At the same time, with the rapid deve ...
Imaging systems can be designed using examples and methods similar to the techniques used in deep learning. We describe experimental results demonstrating optical tomography based on the learning approach. ...
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 ...
A key aspect of constructing highly scalable Deep-learning microelectronic systems is to implement fault tolerance in the learning sequence. Error-injection analyses for memory is performed using a custom hardware model implementing parallelized restricted ...
In this paper we develop a multiagent simulation model to explore the impact of learning dynamics on the productive implementation of innovations in project networks comprised of designers and contractors. Though researchers generally agree that when firms ...
We propose an algorithm to learn from distributed data on a network of arbitrarily connected machines without exchange of the data-points. Parts of the dataset are processed locally at each machine, and then the consensus communication algorithm is employe ...
Reinforcement learning in neural networks requires a mechanism for exploring new network states in response to a single, nonspecific reward signal. Existing models have introduced synaptic or neuronal noise to drive this exploration. However, those types o ...
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or as different experts trying to solve the same task. Our main contribution is ...
We report on the use of deep learning algorithms to perform depth recovery in multiview imaging. We show that if enough training data are provided, a neural network such as multilayer perceptron can be trained to recover the depth in multiview imaging as a ...
This paper presents realization and the laboratory tests of the Kohonen winner takes all (WTA) neural network (NN) realized on microcontrollers (μC) with the AVR and ARM CortexM3 cores. Both μCs have been placed on a single testing board especially designe ...