Table of contents:
- What resources should I use to get started with Deep Learning?
- What resources should I use to get started with Natural Language Processing?
- What research topic should I work on?
- What is a common dataset for my task?
- What is the state-of-the-art for my task?
- What service or template should I use for starting a blog?
I get regularly asked certain questions. Rather than reiterating the answers, I've put them up here so they are easy to find.
What resources should I use to get started with Deep Learning?
Read the Deep Learning book. It is available as a pdf or on Amazon. If you're new to Machine Learning, take the Coursera Machine Learning course by Andrew Ng. For a more complete overview of ML online courses, have a look at this excellent Medium post. In terms of Deep Learning online courses, take the courses offered by fast.ai.
What resources should I use to get started with Natural Language Processing (NLP)?
If you're serious about learning NLP, I would recommend to study the fundamentals first by reading Speech and Language Processing, 2nd Edition by Jurafsky and Martin. The 3rd edition is in progress and some chapters are available as pdf. For learning about Deep Learning for NLP, take the Stanford online course and read Yoav Goldberg's primer. A great practical and code-first introduction to NLP is the fast.ai NLP course.
What research topic should I work on?
I have collected research directions around transfer learning and NLP that might be of interest to you.
What is a common dataset for my task?
Have a look at this collection of datasets for many common NLP tasks.
What is the state of the art for my task?
What service or template should I use for starting a blog?
I am using Ghost with GitHub Pages, which has worked for me but requires some maintenance. For starting a blog from scratch, the easiest way is via the fast.ai template, which is entirely free, requires no coding, and relies on git and Jekyll behind the scenes.