After spending a year working on Machine Learning projects, I finally decided to blog about my experience and perspectives that I have developed over the course of time. This is the first article from a series of upcoming articles discussing my work in the field of Biomedical Image Processing. I hope you all find it worth reading!
Hey,
Can someone kindly help me how to conduct research and possible research ideas in Deep Learning? Any suggestions?
I would love to explore the field further in these Summers. Just need some ideas as a starting point.Thanks!
Thankyou so much Nirant! This was more than what I expected. A really compehensive answer and a pretty good starting point for me! :D
Thanks for all the motivation. I'll spend my summers...
Hello Anuj,
There is no correct answer to How to Publish your first Deep Learning Paper?
Here is how I'd do this, if I were to start now:
In an ideal world, a researcher with an idea could easily build on top of what has already been done (the 90%) and have 10% of work left to do in order to test his or her hypothesis. ... In practice, quite the opposite is happening. Researchers spend weeks re-doing data pre- and post-processing and re-implementing and debugging baseline models.
The difficulty of building upon other’s work is a major factor in determining what research is being done. The majority of researchers build on top of their own research, over and over again. ... I believe the main reason for this is that it’s easiest, from an experimental perspective, to build upon one’s own work. .... Baselines are already implemented in familiar code, evaluation is setup, related work is written up, and so on.
It also leads to less competition – nobody else has ...
I have been carrying out some experiments to recognise hand written characters from binary image forms through transfer learning from EMNIST data which is an extension of MNIST covering all Alphabets.
As we know MNIST data contains DN (digital number) in range 0-255, same is the case with EMNIST, so to perform transfer learning, I preferred to convert the EMNIST data into binary form. Results weren't that great, so I thought why not have a discussion on open forum.
The original black and white (bilevel) images from NIST were size normalized to fit in a 20x20 pixel box while preserving ...
Right there wasn't much loss of data, basically I have to train a model for binary images produced after scanning. Since, NIST is a rich database for hand written characters, transferring know...
Did you look at the data after binarizing it?
Also. Note that you are loosing some amount of information when you binarize. But I don't think you are loosing much, so e...
I wrote an essay about the experience of studying deep learning, sort of a time capsule of my current understanding of many of the fundamentals and current practice. It's a long form essay but may be of interest to those students less advanced. Cheers.