Recently, I have published an article on Journal of Chemical Physics, entitled Tree based machine learning framework for predicting ground state energies of molecules (link to article and preprint). The article discusses in detail, the application of machine learning algorithms to predict ground state energies of molecules. Current standard of computationally efficient electronic structure... Read more
Deep Learning for NLP Best Practices
Table of contents: Introduction Best practices Word embeddings Depth Layer connections Dropout Multi-task learning Attention Optimization Ensembling Hyperparameter optimization LSTM tricks Task-specific best practices Classification Sequence labelling Natural language generation Neural machine translation Introduction This post is a collection of best practices for using neural networks in Natural Language... Read more
Building Random Forest Classifier with Python scikit-learn
In the Introductory article about random forest algorithm, we addressed how the random forest algorithm works with real life examples. As continues to that, In this article we are going to build the random forest algorithm in python with the help of one of the best Python machine learning libraryScikit-Learn. To build the random... Read more
Source Although data about faculty salaries at private universities can be difficult to find, getting data regarding faculty salaries at public universities is much easier. I’ve always been curious (even though I don’t want to go into academia myself!) which fields pay the best and why and if there... Read more
Uber Turns to Neural Network Tech to Enhance Prediction
For Uber, the arrival of peak travel days like New Year’s Eve can strain its service to the limit, with the number of rides nearly tripling its average rate. Consequently, it’s critical for Uber to develop accurate forecasting methods to forecast the volume and location of ride demand. To... Read more
Farmer’s Markets
A series of data visualizations on Farmers’ Market data from data.gov. Dataset Properties Name Location (lat, long, city, state, address) Hours of operation Different goods categories and a yes/no if they’re available at that market UNDERSTANDING THE DATASET I made the following graphic to understand the distribution of the 29 goods... Read more
3 Powerful Applications of Using Analytics-as-a-Service
Analytics-as-a-Service is the combination of analytics software and cloud technology. Instead of hosting any analytics software on premises using your own servers, you use a ready-to-go solution that is easy to deploy and most of the time has a pay-as-you-go payment system. It is part of a larger ‘as-a-Service’... Read more
Regularization, continuity, and the mystery of generalization in Deep Learning
A light and short note on a dense subset of a large space… There’s increasing interest in the very happy problem of why Deep Learning methods generalize so well in real-world usage. After all, Successful networks have ridiculous amounts of parameters. By all rights, they should be overfitting training... Read more
Learning Deep Learning Series Part 1: Videos
Intro. How I Plan to Teach Myself Deep Learning Using Only Free Resources Learning Deep Learning Series Part 1: Videos Learning Deep Learning Part 2: Online Courses Learning Deep Learning Part 3: Github Repos Last week Open Data Science published an article about how I plan to teach myself... Read more
Principal Component Analysis Tutorial
The Problem Imagine that you are a nutritionist trying to explore the nutritional content of food. What is the best way to differentiate food items? By vitamin content? Protein levels? Or perhaps a combination of both? Knowing the variables that best differentiate your items has several uses: 1. Visualization.... Read more