Data Science Austria

5 Ways Artificial Intelligence and Chatbots Are Changing Education

Artificial Intelligence (AI) and Chatbots are changing the world in more ways we can ever imagine. Completing a diversified range of tasks, AI and Chatbots have become a normal element in our everyday life. The technology has played an important role in the development of varied fields including education and … Read more5 Ways Artificial Intelligence and Chatbots Are Changing Education

Review: G-RMI — Winner in 2016 COCO Detection (Object Detection)

A Guide to Select a Detection Architecture: Faster R-CNN, R-FCN and SSD This time, G-RMI, Google Research and Machine Intelligence, who won the 1st place in 2016 MS COCO detection challenge is reviewed. G-RMI is the team name attending the challenge. It is not a name for a proposed approach. Because … Read moreReview: G-RMI — Winner in 2016 COCO Detection (Object Detection)

Brexit: The Uncivil War showed us how the EU Referendum was won with Data Science

Ash NewBlockedUnblockFollowFollowing Jan 11 Something that wasn’t discussed as much as it should have after the release of Channel 4 / HBO’s Brexit The Uncivil War last week was how the extensive use of data science was the main reason that the Leave campaign won against all the odds. In … Read moreBrexit: The Uncivil War showed us how the EU Referendum was won with Data Science

Data Cleaning , Detection and Imputation of Missing Values in R Markdown — Part 2

Data cleaning and transforming variables in R using Australian Tennis Open data on the Men’s tour from 2000 to 2018. Photo by The Creative Exchange on Unsplash Today is Day 4 and marks the continuation of my #29dayproject bootcamp of data science and things I have learnt in data science. This … Read moreData Cleaning , Detection and Imputation of Missing Values in R Markdown — Part 2

One-Hot Encoding is making your Tree-Based Ensembles worse, here’s why?

I am a Master’s Student in Data Science at the University of Virginia and I am working on lots of Machine Learning Projects. Every week, I will be addressing one problem that I faced when working on a project along with a practical solution. Image Credits Most real-world datasets are … Read moreOne-Hot Encoding is making your Tree-Based Ensembles worse, here’s why?

Trust Region and Proximal Policy Optimization

Photo from Deepmind Welcome to another journey towards unraveling the secrets behind Reinforcement Learning. This time, we going to take a step back and return to policy optimization in order to introduce two new methods: trust region policy optimization (TRPO) and proximal policy optimization (PPO). Remember that in policy gradients techniques, … Read moreTrust Region and Proximal Policy Optimization

A Non-Technical Reading List for Data Science

The main idea of How Not to be Wrong is similar as Ellenburg takes us through stories showing both the use and misuse of statistical concepts like linear regression, inference, Bayesian inference, and probability. Applying the laws of probability show us that playing the lottery is always a losing proposition, — except … Read moreA Non-Technical Reading List for Data Science

Optimizing Neural Networks — Where to Start?

Setting up the Environment We’ll use Google Colab for this project, so most of the libraries are already installed. Since we’ll train neural networks, it’s important to use GPU to speed up training. To enable GPU, just go to “Runtime” in the dropdown menu and select “Change runtime type”. You … Read moreOptimizing Neural Networks — Where to Start?

HyperNEAT: Powerful, Indirect Neural Network Evolution

HyperNEAT: Powerful, Indirect Neural Network Evolution Expanding NeuroEvolution Last week, I wrote an article about NEAT (NeuroEvolution of Augmenting Topologies) and we discussed a lot of the cool things that surrounded the algorithm. We also briefly touched upon how this older algorithm might even impact how we approach network building … Read moreHyperNEAT: Powerful, Indirect Neural Network Evolution