Writing papers using Latex – Part 2

crop female designer drawing on paper sheet

After you have gone through the gruesome as well as the exciting task of completing your experiments and getting somewhat positive results for your research publication(maybe even your first). The next step is to prepare it for paper submission at a conference or journal. By now, you should have a working Latex environment and the … Read more

Daily Reads of November 2018

A Medium article that covers the topic of visualizing high-dimensional data using PCA and t-SNE in Python [26/11/2018] Google AI open-sources BERT- A Pretraining model for NLP tasks. This mainly addresses domains that have small amount of labeled data like sentiment analysis and Question-answering. BERT is trained to produce generalized language model representation which we … Read more

Daily Reads of October 2018

An interesting news article on how the future of Healthcare look with AI.[26/10/2018] Check out the article covering a recent review of the Neural History of NLP. [23/10/2018] GoogleAI Research introduces FluidAnnotation which makes image annotations faster and easier.  Previously, an annotator used to carefully click on the boundaries to outline each object in the image, … Read more

Daily Reads of September 2018

Paper : An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation [Paper][doc2vec paper]. [27/09/2018] A good exploration might be to vist DeepDive datasets and application.[25/09/2018] Datasets pertaining to India is available at Machine Learning India.[25/09/2018] MIT Technology Review’s topic on Intelligent Machines post interesting articles from time to time[24/09/2018] Google’s AutoML – … Read more

Daily Reads of August 2018

CommonCrawl archive contains 3.4 billion web pages and 270+ TiB of uncompressed content, crawled between February 17th and Feb 26th.[11/09/2018] CORE ranking of Computer Science conferences [26/08/2018] What is ablation study in Deep Learning. Read this answer on Quora [15/08/2018] Read this Quora answer on Preparing Resume for a Data Science position [06/08/2018]

Daily Reads of July 2018

You can go through my answers given on Quora If you are starting to write your first research paper and are seriously struggling, you can follow this self-help series by Prof. Jari Saramäki. I found it very useful and am still going through it. [22/07/2018] List of upcoming AI Conference deadlines in the field of : Machine Learning,  Computer … Read more

Writing papers using Latex – Part 1

a woman studying inside the library

After you have gone through the gruesome as well as the exciting task of completing your experiments and getting somewhat positive results for your research publication(maybe even your first). The next step is to prepare it for paper submission at a conference or journal. Most conferences will follow the proceedings template of either ACM (generally, … Read more

Sept 2018 Research Jobs

Post title – Research Assistant (Application portal – IIT Kharagpur temporary jobs) Number of posts – 1 Last date to apply – 6th September, 2018 Salary – Upto Rs. 25000/- (salary equivalent to a Junior Research Fellow) Minimum qualifications – B.Tech in Computer Science and related works with first division marks Project – Learning Representations from … Read more

Working with Imbalanced Data sets

Theory Imbalanced data sets, in the context of supervised classification problems, refer to the case when the class distribution is highly skewed or disproportionate. Since general supervised learning algorithms assume them to be balanced, they perform accuracy maximization. However, this, in turn, will propagate a model bias and be addressed to some extent, when we … Read more

Exploratory Analysis using R

This is a good post on making visualisations with pandas data frame in Python. It covers uni-variate plots like histograms, line plots, density plots and multivariate plots like correlation plot matrix and scatter-plot matrix. Before diving into feature engineering and data cleaning, it is a good idea to have a good understanding of the data. … Read more