Jinoo BaekA Simple Example of Causal Attention Masking in Transformer DecoderThis is a note to help myself understand the look-ahead-attention-masking in the decoder stack of a Transformer, an artificial neural…Sep 6, 2021Sep 6, 2021
Jinoo BaekA Simple Example of Batch NormalizationThis is a summarization of an attempt to obtain the analytical solution to back-propagation in a batch normalization layer (as part of…Jul 17, 2018Jul 17, 2018
Jinoo BaekMy Journey into Deep LearningOver the last year, I finished three classes (two Udacity Nanodegrees and one Stanford University online class audit) to learn how to make…Jul 17, 2018Jul 17, 2018