Weekly Selection — Mar 8, 2019
What are the most pressing problems in data science? Take our survey
One neural network, many uses
By Paras Chopra — 15 min read
It’s common knowledge that neural networks are really good at one narrow task, but they fail at handling multiple tasks. This is unlike the human brain which is able to use the same concepts at amazingly diverse tasks.
OpenAI GPT-2: Understanding Language Generation through Visualization
By Jesse Vig — 9 min read
In the eyes of most NLP researchers, 2018 was a year of great technological advancement, with new pre-trained NLP models shattering records on tasks ranging from sentiment analysis to question answering.
Learning to Plan with Value Iteration Networks
By Or Rivlin — 9 min read
The first major achievement of deep reinforcement learning was the famous DQN algorithm’s human level performance in various Atari video games, in which a neural network learned to play the game using the raw screen pixels as input.
Using word2vec to Analyze News Headlines and Predict Article Success
By Charlene Chambliss — 17 min read
Can word embeddings of article titles predict popularity? What can we learn about the relationship between sentiment and shares? word2vec can help us answer these questions, and more.
Interpretable AI or How I Learned to Stop Worrying and Trust AI
By Ajay Thampi — 13 min read
In the last five years alone, AI researchers have made significant breakthroughs in areas such as image recognition, natural language understanding and board games!
Being a Data Scientist does not make you a Software Engineer!
By Semi Koen — 11 min read
Hopefully I caught your attention with the controversial title. Great! Now bear with me as I am going to show you how you can build a scalable architecture to surround your witty Data Science solution!
Build your own Robust Deep Learning Environment in Minutes
By Dipanjan (DJ) Sarkar — 15 min read
Thanks to cheaper and bigger storage we have more data than what we had a couple of years back. We do owe our thanks to Big Data no matter how much hype it has created.
Getting started with Git and GitHub: the complete beginner’s guide
By Anne Bonner — 2 min read
Git and GitHub basics for the curious and completely confused (plus the easiest way to contribute to your first open source project ever!)
A Gold-Winning Solution Review of Kaggle Humpback Whale Identification Challenge
By Vladislav Shakhray — 10 min read
Recently, my team took part in Humpback Whales Identification Challenge hosted on Kaggle. We won a gold medal and were placed at #10 (out of 2131 teams) on the leaderboard.
Will the Sun Rise Tomorrow? Introduction to Bayesian Statistics for Machine Learning
By Matthew Stewart, PhD Researcher — 11 min read
Have you ever asked yourself what is the probability that an event will occur that has previously never occurred?
Simplifying the ROC and AUC metrics.
By Parul Pandey — 8 min read
ROC and AUC curves are important evaluation metrics for calculating the performance of any classification model. These definitions and jargons are pretty common in the Machine learning community and are encountered by each one of us when we start to learn about classification models.
Preserving Memory in Stationary Time Series
By Simon Kuttruf — 8 min read
Many predictive models require a certain consistency of time series called stationarity. The usual transformation, namely integer order differencing (in Finance e.g. modelling returns instead of absolute prices), eliminates memory in the data and hence affects the predictive power of the modelling.
