Deep Learning for premitives [part 1].
1. Who is better ? Human or computer ?
This article is the first among a series of articles, through which I believe I could share what I know in deep learning in a very simplified and casual way, so that no one else should sweat to grasp the fundamental ideas of deep learning as I did. There are already a few other people who does the same simplification proces of these concepts, and I would like to contribute this series as well, to that collection. I will be focusing on these two things while writing this, 1. not to exclude underlying math entirely ( including simple explanations ) 2. demo coding in simple languages, lua (Torch) & processing.
Breaking down 'language transliteration' ( phonetic translation ) Project ( version 1 ).
As my first academic project, I’ve chose to develop a self learning English - Malayalam phonetic transliterator, where the end user could type in Malayalam words by their phonetic alternatives through a English keyboard. Although such commercial projects are already available, I’ve decided to give it a try through my own implementation, as a babystep towards modelling self learning algorithms. The backbone of this project is made up of basic probability theory and operations, with which both decision making and learning mechanisms are functioning. Here’s a brief note on how it is done:
I struggled a lot to get started this first article as a minimalist. How I decided best suitable tools for me.
Writing a blog was a painful task for me. I’ve tried different tools and services available, as my friends and other writers suggested. It was painful to write and publish articles, but its even more complicated to maintain the text content on the go. So, after a long break I’ve decided to give it a try (It may take another full page to explain why now). This time, I wanted to throw myself into analysis on what tools and writing environments I actually wanted.