Using deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.
created at Nov. 26, 2016, 2:41 p.m.
Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye.
created at Aug. 25, 2017, 8:33 p.m.
Auto-optimizing a neural net (and its architecture) on the CIFAR-100 dataset. Could be easily transferred to another dataset or another classification task.
created at May 27, 2017, 6:15 p.m.