Engineer | Machine Learning Researcher | Gamer
A few years ago a friend of friend introduced me to a data set known as the Global Database of Events Language and Tone (GDELT) data. GDELT is an open source event data repository based on news articles and currently contains over a quarter-billion event records starting from the year 1979. The database is updated [...]
This is just a list of online resources for getting started with Data Science. I only list resources that I have used, recommended by a lecture or where I have done a brief walk-trough to fill some knowledge gaps. Courses for absolute beginners: Coursera: Data Science Specialization LinkedIn Learning: Data Science foundations Udemy: Complete Python [...]
Oh wow, it is September and we are heading towards the end of 2019. What have you achieved? Did you get your dream job? have you started a new career? learned something new about your self? Did you meet the love of your life? Attained your fitness goals. Well for me it feels like I [...]
Data Science is currently marketed as a skill/career that anyone can learn. If you can write code you can become a Data Scientist. Ok, that is an argument for another day. However, because of this marketing and hype surrounding AI (Artificial Intelligence ), it is no surprise that I have crossed paths with Data Scientists [...]
If you have any interest in the field of machine learning and artificial intelligence (AI), then you must have come across neural networks. I like to think of a neural network as a computer program that learns how to accomplish specific tasks with the help of lots and lots of data. Probably a very common [...]
Overview In the previous post we looked at backpropagation. In the example we calculated the gradient of the loss with respect to each weight parameter. The gradient determined which direction to move the weight parameter and how much to move it by. The new weight parameter was then updated using the formula below: $latex w_{new} [...]
In this post I will go through a simple backpropagation algorithm that I have implemented on a spreadsheet. It is simple as I will use one training example with two input features to explain the concept. For example: A single training example In the above we have a single observation with two input variables x1 [...]
