NullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representations of Feature Maps.
Alessandro AimarHesham MostafaEnrico CalabreseAntonio Rios-NavarroRicardo Tapiador-MoralesIulia-Alexandra LunguMoritz B. MildeFederico CorradiAlejandro Linares-BarrancoShih-Chii LiuTobi DelbrückPublished in: IEEE Trans. Neural Networks Learn. Syst. (2019)
Keyphrases
- sparse representation
- feature maps
- convolutional neural network
- dictionary learning
- face detection
- face recognition
- sparse coding
- image classification
- self organizing maps
- dimensionality reduction
- saliency map
- kernel function
- neural network
- high dimensional data
- feature space
- training samples
- signal processing
- object detection
- feature vectors
- similarity measure
- data sets
- image retrieval
- fuzzy neural network