2019 has been a year of gatsby updates for this site. So, I wanted to end this year with the same spirit. And, I am hoping this is going to be the begining of maturity of the looks and features of this blog. In the upcoming year, I plan to focus mainly on content, specifically related to medicine, AI and proramming. TLDR Updates to this blog UI: Using prism-react-renderer to enable custom code blocks with copy to clipboard button Medium-like highlight text to share goatcounter for analytics Here is a list of all the new features that I have lately added to this:
First of all, apologies for a sudden update of the domain name - from datasciencevision.com to the new address reckoning.dev! I let the old address lease expire and opted for a new (hopefully better!) home for this blog. The code base has also moved to a new repository. Along with the updated address, you will also a find few big and many small changes in the looks of the overall theme.
Managing multiple research experiments at a time can be overwhelming. The same applies to deep learning research as well. Beyond the usual challenges in software development, machine learning developers face new challenges - experiment management (tracking which parameters, code, and data went into a result) and reproducibility (running the same code and environment later)! UPDATE Recently, I was contacted by Gideon Mendels, CEO of comet.ml regarding the issues that I reported on this post.
As a researcher, I have to keep myself up-to-date with latest research in my field. Given the pace with which deep learning research is moving currently, it has become quite a gargantuan task lately. Large quantity also brings a lot of noise with it. While, whether certain works should really be published is a matter of discussion for another day! As a researcher it has become quite impossible to read each and every one of papers that show up on Arxiv in the my field of deep learning, computer vision and pattern recognition.
Lately, a lot of my friends have been asking about my deep learning workstation setup. In this post I am going to describe my hardware, OS, and different packages that I use. In particular, based on the question, I found that the most of the interest have been around managing different python versions, and modules like pytorch/tensorflow libraries etc. Workstation Hadware Here are the configurations of my workstation: Intel - Core i7-8700 3.
Modeling the relationship between a scalar response (or dependent variable) and one or more explanatory variables (or independent variables) is commonly referred as a regression problem. The simplest model of such a relationship can be described by a linear function - referred as linear regression. Mathematical formulations Linear Regression represents a linear relationship between the input variables ($X$) and single output variable($y$). When the input ($X$) is a single variable, this model is called Simple Linear Regression and when there are multiple input variables ($X$), it is called Multiple Linear Regression.