An algorithm is, in general, a procedure for solving a particular problem (or set of problems). Today, however, they are most often thought about in the context of computers, and, as such, this tag will frequently appear alongside the Machine Learning category.

The above image is a visual depiction of a Merge Sort, an efficient and popular algorithm for general-purpose sorting. Here, the boxes are sorted by brightness, with the lightest boxes appearing at the top.

  • No Free Lunch and Neural Network Architecture
    [Machine Learning] Machine learning must always balance flexibility and prior assumptions about the data. In neural networks, the network architecture codifies these prior assumptions, yet the precise relationship between them is opaque. Deep learning solutions are therefore difficult to build without a lot of trial and error, and neural nets are far from an out-of-the-box solution for most applications.
  • DeepMind's AlphaZero and The Real World
    [Machine Learning] Using DeepMind’s AlphaZero AI to solve real problems will require a change in the way computers represent and think about the world. In this post, we discuss how abstract models of the world can be used for better AI decision making and discuss recent work of ours that proposes such a model for the task of navigation.
  • The Importance of Simulation in the Age of Deep Learning
    [Machine Learning] An overview of the significance of simulation tools in the field of robotics and the promise and limitations of photorealistic simulators.
  • For AI, translation is about more than language
    [Machine Learning] Translation is about expressing the same underlying information in different ways, and modern machine learning is making incredibly rapid progress in this space.
  • Have You Tried Using a 'Nearest Neighbor Search'?
    [Machine Learning] More complicated ≠ better. In many circumstances, using the most sophisticated approaches to Machine Learning (like deep learning) may not be worthwhile.