1. Adam: A method for stochastic optimization;kingma,2014
2. Searching for activation functions;ramachandran,2017
3. Using automatic programming to improve gradient boosting for classification;olsson;Proc Int Conf Artif Intell Soft Comput,2022
4. Incorporating Nesterov momentum into ADAM;dozat;Proc Int Conf Learn Representations,2016
5. Automatic synthesis of neurons for recurrent neural nets;olsson,2022