MatConvNet
2015pp. 689–692
Citations Over TimeTop 1% of 2015 papers
Abstract
MatConvNet is an open source implementation of Convolutional Neural Networks (CNNs) with a deep integration in the MATLAB environment. The toolbox is designed with an emphasis on simplicity and flexibility. It exposes the building blocks of CNNs as easy-to-use MATLAB functions, providing routines for computing convolutions with filter banks, feature pooling, normalisation, and much more. MatConvNet can be easily extended, often using only MATLAB code, allowing fast prototyping of new CNN architectures. At the same time, it supports efficient computation on CPU and GPU, allowing to train complex models on large datasets such as ImageNet ILSVRC containing millions of training examples
Related Papers
- → Simplicity in the Best Systems Account of Laws of Nature(2013)54 cited
- → Naïve Simplicity: The Overlooked Piece of the Complexity‐Simplicity Paradigm(2017)15 cited
- → Simplicity, Inference and Modelling(2002)77 cited
- On the Simplicity of a Scientific Theory(2008)
- Simplicity"Design of Indoor Surroundings Art(2002)