Network Architecture Search (NAS) has achieved great results and generated models comparable with humans’ classifications. Automating the definition of a neural architecture reduces the need for expert work efforts and mitigates human bias from architecture design. NAS techniques usually consist of an algorithm to search for the best architecture in a predetermined space of parameters or functions. Due to the number of deep neural architectures parameters, this search space includes millions of combinations, making NAS a cost procedure and may lead the search to overfit the training set. To reduce NAS search spaces’ complexity and still obtain competitive results, we propose CoNAS, a committee of NAS-based models, by restricting the search spaces to perform Differentiable ARchiTecture Search (DARTS). Our results point to improved accuracy over DARTS on two experimental scenarios: raining from scratch and using a transfer learning approach.