Category:
Machine Learning


As machine learning is a substantive portion of my job nowadays, I'll probably update this description sometime soon...

  • No Free Lunch and Neural Network Architecture
    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.
  • Proxy metrics are everywhere in Machine Learning
    Many machine learning systems are optimized using metrics that don't perfectly match the stated goals of the system. These so-called "proxy metrics" are incredibly useful, but must be used with caution.
  • DeepMind's AlphaZero and The Real World
    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
    An overview of the significance of simulation tools in the field of robotics and the promise and limitations of photorealistic simulators.
  • Practical Guidelines for Getting Started with Machine Learning
    The potential advantages of AI are many, and using machine learning to accelerate your business may outweigh potential pitfalls. If you are looking to use machine learning tools, here are a few guidelines you should keep in mind.
  • For AI, translation is about more than language
    Translation is about expressing the same underlying information in different ways, and modern machine learning is making incredibly rapid progress in this space.
  • Bias in AI Happens When We Optimize the Wrong Thing
    Bias is a pervasive problem in AI. Only by discouraging machine learning systems from exploiting a certain bias can we expect such a system to avoid doing so.
  • My Favorite Deep Learning Papers of 2017
    Here are five deep learning papers I felt rose above the rest in 2017.
  • Have You Tried Using a 'Nearest Neighbor Search'?
    More complicated ≠ better. In many circumstances, using the most sophisticated approaches to Machine Learning (like deep learning) may not be worthwhile.