Recent Posts

TensorFlow - A fast Introduction An open source library for numerical computation using data flow graphs Okay, so what is it? Hmm, In short, it’s a wonderful library provided by google for general purpose Machine Learning problems, specially with deep learning. Problems could be a Visual Recognition, Machine Translation , Natural Language Processing (NLP) or even simple linear regression. By the way, it have made the researchers/ developers life easy by providing tons of pre-defined packages or high level utility programs , like tensorboard.


A data file contains daily values of the Straits Times Index (STI) from 1 Jan’04 to 31 Dec’13 . The fields are: – Date – Opening Price – Closing Price – Adjusted Close (similar to above but after minor accounting changes) – Highest value during the day – Lowest value during the day – Volume (total amount of traded stocks during the day) Goal: The goal is to predict the short term STI trend with sufficient accuracy for profitable use in a (simplified) trading scenario


Welcome to the world. Its 2017 now.



Human Activity Recognition

Making sense of data from modality sensors for robust human action recognition. Then develop an algorithm that would classify the different activities into categories using either data from single sensor or from fusion of multiple sensors.

Sign Language Recognition

Word recognizer for American Sign Language video sequences, utilizing the probabalistic models


  • sunil-prakash
  • Singapore