Category:

Machine Learning

Particularly for safety-critical applications or the automation of tasks that can directly impact quality of life, we must be careful to avoid the valley of AI trust—the dip in overall safety caused by premature adoption of automation.

Recent ire from the media has focused on the high-power consumption of artificial neural nets (ANNs), yet popular discussion frequently conflates training and testing. Here, I aim to clarify the ways in which conversations involving the relative efficiency of ANNs and the human brain often miss the mark.

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.

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.

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.

An overview of the significance of simulation tools in the field of robotics and the promise and limitations of photorealistic simulators.

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.

Translation is about expressing the same underlying information in different ways, and modern machine learning is making incredibly rapid progress in this space.

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.

Here are five deep learning papers I felt rose above the rest in 2017.

More complicated ≠ better. In many circumstances, using the most sophisticated approaches to Machine Learning (like deep learning) may not be worthwhile.