NoAS-DS: Neural optimal architecture search for detection of diverse DNA signals

Kaushik Bhargav Sivangi, Chandra Mohan Dasari, Santhosh Amilpur, Raju Bhukya

Abstract: Highlights•NoAS-DS perpetually designs architectures for sequence-based classification tasks.•A combination of convolution and LSTM layers is used in NoAS-DS.•DNA computing methodology is used to encode information related to architecture.•The optimal models generated by NoAS-DS have outperformed state-of-the art methods.•Transfer learning is employed to assess the architectures’ generalization ability.