
This post talks about how to use a biLSTM neural network to learn wordlevel and characterlevel representations and predict PoS tagging. The model achieves the stateofart performance on the CoNLL2000 dataset.

This post briefly talks about common activation functions and gradient optimizers used in deep learning.

This post briefly talks about relevant mathematical concepts from linear algebra, calculus, probability, and optimization, which are discussed in detail to lay the mathematical foundation required for deep learning.

This post briefly provides a guide on the design of MapReduce algorithms. In particular, it presents a number of "design patterns" that capture effective solutions to common problems.

This post briefly talks about basics on MapReduce. Topics on mappers, reducers, partitioners, and combiners are included.

This post briefly talks about what antoencoders are and how to build them to compress and denoise images in TensorFlow.