13 Mar 2020
The Valley of AI Trust
[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.
30 Dec 2019
Machine Learning & Robotics: My (biased) 2019 State of the Field
My thoughts on the past year of progress in Robotics and Machine Learning.
07 Aug 2019
On the efficiency of Artificial Neural Networks versus the Brain
[Machine Learning] 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.
24 May 2019
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.
25 Jan 2019
Proxy metrics are everywhere in Machine Learning
[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.
09 Jan 2019
Massive Datasets & Generalization in ML
[Machine Learning] Big, publically available datasets are great. Yet many practitioners who seek to use models pretrained on this data need to ask themselves how informative the data is likely to be for their purposes. Dataset bias and task specificity are important factors to keep in mind.
16 Dec 2018
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.
01 Dec 2018
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.
05 Sep 2018
Practical Guidelines for Getting Started with Machine Learning
[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.
03 Sep 2018
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.
29 Jul 2018
Bias in AI Happens When We Optimize the Wrong Thing
[Machine Learning] 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.
27 Dec 2017
My Favorite Deep Learning Papers of 2017
[Machine Learning] Here are five deep learning papers I felt rose above the rest in 2017.