Machine learning
- 1. Machine Learning Machines that learn By: Mayank Shekhar
- 2. What is Machine Learning? A comic strip by Tom Gauld
- 3. Why is Machine Learning important? A visual representation of Yoshua Bengio's "learning model," where machines "think" about faces and emotions. Image: Courtesy Yoshua Bengio NETFLIX recommender system knows you better than you know yourself! Source: https://www.wired.com/2013/06/yoshua-bengio/
- 4. How does Machine Learning work? Supervised Learning - input data and corresponding output data Unsupervised Learning - Only input data
- 5. What’s the difference between AI and Machine Learning? Artificial Intelligence is the broader concept of machines being able to carry out tasks in a way that we would consider “smart”. And, Machine Learning is a current application of AI based around the idea that we should really just be able to give machines access to data and let them learn for themselves. Source: https://www.forbes.com/sites/bernardmarr/2016/12/06/what-is-the-difference-between-artificial-intelligence-and-machine-learning/#40878cdf2742
- 6. Drawbacks Limited hardware support Large input data requirements Unsupervised learning still in development phase Needs GPU
- 7. What can be expected in the future? The most powerful form of machine learning being used today, called “deep learning”, builds a complex mathematical structure called a neural network based on vast quantities of data. Designed to be analogous to how a human brain works, neural networks themselves were first described in the 1930s. But it’s only in the last three or four years that computers have become powerful enough to use them effectively. If deep learning will be as big as the internet, it’s time for everyone to start looking closely at it! Source: https://www.theguardian.com/technology/2016/jun/28/google-says-machine-learning-is-the-future-so-i-tried-it-myself
- 8. Google’s DeepMind AI, developed by researchers at Google, learns without human input. DeepMind AI is a big deal because it was able to beat a “human” champion at the game of “Go” (a Chinese game), which has 10^1023 possible situations. If the number doesn’t make sense then there are “only” 10^82 atoms in the observable universe. DeepMind Technologies' goal is to "solve intelligence", which they are trying to achieve by combining "the best techniques from machine learning and systems neuroscience to build powerful general-purpose learning algorithms". Image source: https://xkcd.com/894/
- 9. Thank you!