AGI: When will we get there ?

THE SCIENTIFIC method was perhaps the single most important development in modern history. It established a way to validate truth at a time when misinformation was the norm, allowing natural philosophers to navigate the unknown. From predicting the motions of

Array Programming with Numpy

Numpy is open source numeric and scientific computations library created around 2005. Numpy is also highly popular in scientific community and has recently been used to perform computations needed to discover black holes and gravitational waves. It provides a multidimensional

Strategies for Preventing model overfitting

Overftting is typically a result of using too complex models, and we need to choose a proper model complexity to achieve the optimal bias-variance tradeoff. Cross-validation and Regularization are two key techniques in machine learning to prevent overfitting. 1. Cross-validation:

What is the bias-variance tradeoff?

In this blog post we will try to cover the following questions: 1. What’s the bias-variance trade-off? 2. How’s this tradeoff related to overfitting and underfitting? 3. How do you know that your model is high variance, low

A long introduction to Machine Learning

Machine learning is closely related to Artificial intelligence * AI is about building machines or intelligent agents that exhibit intelligence. * ML enables machines to learn from experience, and is a sub-field of AI. * Deep learning focuses on a family of learning

Four useful data Analysis concepts

"The first principle is that you must not fool yourself, and you are the easiest person to fool." Cone of Possibilities Designers use a similar process [2]. Mature designer have a structured way of thinking where he/she