Somshubra Majumdar

Keras implementation of [The unreasonable effectiveness of the forget gate](https://arxiv.org/abs/1804.04849)

titu1994

Implementation of the LAMB optimizer for Keras from the paper "Reducing BERT Pre-Training Time from 3 Days to 76 Minutes"

titu1994

U-Net Model conditioned with MobileNet features for Grayscale -> Color mapping

titu1994

Miltiplicative LSTM for Keras 2.0+

titu1994

A Keras implementation of Neural Arithmatic and Logical Unit

titu1994

Wrapper for Normalized Gradient Descent in Keras

titu1994

Keras implementation of Octave Convolutions

titu1994

Implementation of One-Cycle Learning rate policy (adapted from Fast.ai lib)

titu1994

Keras implementation of Padam from "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks"

titu1994

Implementation of ResNeXt models from the paper Aggregated Residual Transformations for Deep Neural Networks in Keras 2.0+.

titu1994