We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Jet Features: Hardware-Friendly, Learned Convolutional Kernels for High-Speed Image Classification.
- Authors
Simons, Taylor; Lee, Dah-Jye
- Abstract
This paper explores a set of learned convolutional kernels which we call Jet Features. Jet Features are efficient to compute in software, easy to implement in hardware and perform well on visual inspection tasks. Because Jet Features can be learned, they can be used in machine learning algorithms. Using Jet Features, we make significant improvements on our previous work, the Evolution Constructed Features (ECO Features) algorithm. Not only do we gain a 3.7× speedup in software without loosing any accuracy on the CIFAR-10 and MNIST datasets, but Jet Features also allow us to implement the algorithm in an FPGA using only a fraction of its resources. We hope to apply the benefits of Jet Features to Convolutional Neural Networks in the future.
- Subjects
DIFFERENTIAL evolution; INSPECTION &; review; MACHINE learning; CLASSIFICATION; ALGORITHMS; IMAGE
- Publication
Electronics (2079-9292), 2019, Vol 8, Issue 5, p588
- ISSN
2079-9292
- Publication type
Article
- DOI
10.3390/electronics8050588