ashish
If you have been reading up on machine learning and/or deep learning, you have probably encountered Kullback-Leibler divergence [1]. It is commonly used to measure loss in machine learning -…
Read more
ashish
You wanted to build deep learning networks. You discovered TensorFlow library through a Google search or Udacity course and decided to try it out, as you like Python. You looked…
Read more
ashish
Recently concluded Bay Area DL School Organized by Andrew Ng, Samy Bengio, Pieter Abbeel and Shubho Sengupta was an excellent event to understand the state of art in Deep Learning…
Read more
ashish
In the first part of self-driving cars, I talked about impacts to insurance and licensing regimes. There are some very exciting opportunities to empower people with disabilities. There are a…
Read more
ashish
In part I we talked about some simple features that can be extracted from just the date fields. We extracted 9 features. This part takes it to the next level.…
Read more
ashish
Feature engineering is often the most important part… is what research on winning Kaggle’rs by David Wind reveals. It is somewhat ignored in the texts about machine learning, which seem…
Read more