Artificial intelligence and machine learning have risen greatly both in terms of their popularity and applications in recent years. We’ve seen how machine learning has been used to create formidable opponents at popular games like Go and we’ve also seen how it can be a powerful technique to explore areas like dark matter, optimum advertisement strategies, and even pandemics like COVID-19.
But much of the existing literature on machine learning, barring a few resources, can come off as abstruse and pedantic. Considering this, Google has taken an initiative called AI Explorables to make the core concepts of machine learning more accessible via a series of interactive explanations.
|Hidden Bias||Measuring Fairness|
Currently, Google has posted explanations of two fundamental concepts—Hidden Bias and Measuring Fairness. But in the coming months, the tech giant plans on posting more ‘Explorables’ on other fairness issues such as the effect of feedback loops on the biases of the AI system. Interpretability, which answers the logical steps taken by a system to reach a specific point, will be covered too along with the issue of privacy and what it means in the context of an AI system.