Transfer Learning, Finding Learning Rate, and More

Training a neural network from scratch is unnecessary in a situation when pretrained models are readily available. This notebook showcases loading a pretrained model directly from pytorch.models subpackage, its subsequent re-training for the specific problem at hand, a method used Read the rest

ΠΕΡΣΈΠΟΛΙΣ Γ (Persepolis Gamma) @ YouTube

Originally written in February 2010. as a required piece for chamber string ensemble during my 3rd year as a student of undergraduate composition program under mentorship of professor Milan Mihajlović. Revised for the guitar ensemble during recording sessions in 2019. Read the rest