Jekyll2021-05-07T20:24:19-05:00kaggler.com/feed.xmlKaggler TV BlogMade by Kagglers, for Kagglers. Kaggler TV is a YouTube Channel that shares about machine learning competitions and data science career development.TF/Keras BERT Baseline (Training/Inference)2021-05-07T00:00:00-05:002021-05-07T00:00:00-05:00kaggler.com/notebook/kaggle/nlp/2021/05/07/tf-keras-bert-baseline-training-inferencePyTorch Lightning RoBERTa Baseline (Training/Inference)2021-05-07T00:00:00-05:002021-05-07T00:00:00-05:00kaggler.com/notebook/kaggle/nlp/2021/05/07/pytorch-lightning-roberta-baselineKaggler v0.9.4 Release with Stacked DAE2021-05-01T00:00:00-05:002021-05-01T00:00:00-05:00kaggler.com/kaggler/dae/2021/05/01/kaggler-new-releaseToday, Kaggler v0.9.4 is released with additional features for DAE as follows: In addition to the swap noise (swap_prob), the Gaussian noise (noise_std) and zero masking (mask_prob) have been added to DAE to overcome overfitting. Stacked DAE is available through the n_layer input argument (see Figure 3. in Vincent et al. (2010), “Stacked Denoising Autoencoders” for reference).DAE with 2 Lines of Code with Kaggler2021-04-29T00:00:00-05:002021-04-29T00:00:00-05:00kaggler.com/notebook/kaggle/2021/04/29/dae-with-2-lines-of-code-with-kagglerStacking Ensemble2021-04-26T00:00:00-05:002021-04-26T00:00:00-05:00kaggler.com/notebook/kaggle/2021/04/26/stacking-ensemble