Adaptive data augmentation for image classification
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.
An implementation of an optical perceptron with a soft optical threshold trained with an adapted BP algorithm is described as a precursor to an optical multilayer perceptron (MLP). It has 64 inputs and ten outputs. The soft threshold is implemented by a li ...
The early detection of changes in the level and composition of algae is essential for tracking water quality and environmental changes. Current approaches require the collection of a specimen which is later analyzed in a laboratory: this slow and expensive ...
In this paper, we propose a generalization of convolutional neural networks (CNN) to non-Euclidean domains for the analysis of deformable shapes. Our construction is based on localized frequency analysis (a generalization of the windowed Fourier transform ...
We describe an evolutionary vision system capable of autonomously scanning through an image while zooming in and out and changing filtering strategy in order to perform shape discrimination. The system consists of a small artificial retina controlled by an ...
The authors employ energy-based arguments to establish a robustness and a convergence result for a gradient-descent adaptive law in the presence of both noisy measurements and uncertainty in the initial guess. ...
We propose a recurrent neural-network for real-time reconstruction of acoustic camera spherical maps. The network, dubbed DeepWave, is both physically and algorithmically motivated: its recurrent architecture mimics iterative solvers from convex optimisati ...
Recurrent neural networks based on reservoir computing are increasingly being used in many applications. Optimization of the topological structure of the reservoir and the internal connection weights for a given task is one of the most important problems i ...
In this paper, an automatic synthesis methodology based on evolutionary computation is applied to evolve neural controllers for a homogeneous team of miniature autonomous mobile robots. Both feed-forward and recurrent neural networks can be evolved with fi ...
An implementation of an optical perceptron with a soft optical threshold trained with an adapted BP algorithm is described as a precursor to an optical multilayer perceptron (MLP). It has 64 inputs and ten outputs. The soft threshold is implemented by a li ...
In biomedical signal analysis, artificial neural networks are often used for pattern classification because of their capability for nonlinear class separation and the possibility to efficiently implement them on a microcontroller. Typically, the network to ...