Randomly translational activation inspired by the input distributions of ReLU
Sign Up to like & getrecommendations! Published in 2018 at "Neurocomputing"
DOI: 10.1016/j.neucom.2017.09.031
Abstract: Abstract Deep convolutional neural networks have achieved great success on many visual tasks (e.g., image classification). Non-linear activation plays a very important role in deep convolutional neural networks (CNN). It is found that the input… read more here.
Keywords: input distributions; non linear; proposed method; activation ... See more keywords
All-optical non-linear activation function for neuromorphic photonic computing using semiconductor Fano lasers.
Sign Up to like & getrecommendations! Published in 2020 at "Optics letters"
DOI: 10.1364/ol.395235
Abstract: We predict that semiconductor Fano lasers can be used to realize an all-optical non-linear activation function for neuromorphic photonic computing. By exploiting optical control of a Fano mirror, the laser can generate optical pulses with… read more here.
Keywords: fano; optical non; non linear; semiconductor fano ... See more keywords