Save, Load and Inference From TensorFlow 2.x Frozen Graph 01-09-2020 01-09-2020 blog 6 minutes read (About 826 words)Continuing to Support Frozen Graph for TensorFlow 2.x Machine Learning, Deep Learning, TensorFlow Read More
Word2Vec Models Revisited 08-23-2019 08-23-2019 article 24 minutes read (About 3525 words)A Review on the Classic Word2Vec Models Machine Learning, Natural Language Processing, Optimization Read More
Hierarchical Softmax 08-17-2019 08-17-2019 article 8 minutes read (About 1194 words)Orchestrated Softmax for Fast Language Model Training Machine Learning, Natural Language Processing, Optimization Read More
Label Smoothing 08-11-2019 12-26-2020 blog 6 minutes read (About 956 words)Regularization for Classification Models Machine Learning, Optimization, Regularization Read More
Cross Entropy, KL Divergence, and Maximum Likelihood Estimation 08-10-2019 08-10-2019 blog 6 minutes read (About 942 words)Some Theories for Machine Learning Optimization Machine Learning, Information Theory, Cross Entropy, KL Divergence, Maximum Likelihood Estimation Read More
Noise Contrastive Estimation 07-26-2019 04-17-2024 article 33 minutes read (About 4917 words)Accelerate the Training of Neural Language Models Machine Learning, Natural Language Processing, Optimization Read More
Dropout Explained 06-04-2019 06-04-2019 blog 8 minutes read (About 1155 words)The Math of Dropout You Know and Don't Know Machine Learning, Deep Learning Read More
Introduction to Variational Inference 05-25-2019 05-25-2019 article an hour read (About 7331 words)Setting Up Foundations to Bayesian Learning Machine Learning, Statistics, Variational Inference Read More
Introduction to Bayesian Filter 03-21-2019 03-21-2019 article 9 minutes read (About 1330 words)Restate Some Basic Concepts and Math in Bayesian Filter Machine Learning, Statistics, Bayesian Filter Read More
CycleGAN Voice Converter 06-13-2018 06-13-2018 project 8 minutes read (About 1182 words)CycleGAN-Based Voice Conversions Machine Learning, Deep Learning, Generative Adversarial Networks, Computer Vision Read More