Despite years of hype, virtual reality headsets have yet to topple TV or computer screens as the go-to devices for video viewing. One reason: VR can make users feel sick.… Read More »Using artificial intelligence to generate 3D holograms in real-time
What do Cheetos have in common with plumbing pipes, pharmaceuticals, and windshield wiper blades? They are extruded. And if you extrude things, you know quality control is a big deal.… Read More »How do you make perfect Cheetos? Use AI.
Nearly all real-world applications of reinforcement learning involve some degree of shift between the training environment and the testing environment. However, prior work has observed that even small shifts in… Read More »Maximum Entropy RL (Provably) Solves Some Robust RL Problems
In a perfect world, what you see is what you get. If this were the case, the job of artificial intelligence systems would be refreshingly straightforward. Take collision avoidance systems… Read More »Algorithm helps artificial intelligence systems dodge “adversarial” inputs
Deep learning is advancing at lightning speed, and Alexander Amini ’17 and Ava Soleimany ’16 want to make sure they have your attention as they dive deep on the math… Read More »Retrofitting MIT’s deep learning “boot camp” for the virtual world
There is healthy debate about the productivity of multi-tasking. Is it possible to take excellent notes while also being fully present in a meeting? Now, you don’t have to choose… Read More »New Garage project Group Transcribe helps you transcribe and translate while advancing inclusive speech AI
Traditional computer scientists and engineers are trained to develop solutions for specific needs, but aren’t always trained to consider their broader implications. Each new technology generation, and particularly the rise… Read More »Fostering ethical thinking in computing
In October, a modified Dallara-15 Indy Lights race car programmed by MIT Driverless will hit the famed Indianapolis Motor Speedway at speeds of up to 120 miles per hour. The… Read More »Driving on the cutting edge of autonomous vehicle tech
Our method learns a task in a fixed, simulated environment and quickly adapts to new environments (e.g. the real world) solely from online interaction during deployment.
The ability for humans to generalize their knowledge and experiences to new situations is remarkable, yet poorly understood. For example, imagine a human driver that has only ever driven around their city in clear weather. Even though they never encountered true diversity in driving conditions, they have acquired the fundamental skill of driving, and can adapt reasonably fast to driving in neighboring cities, in rainy or windy weather, or even driving a different car, without much practice nor additional driver’s lessons. While humans excel at adaptation, building intelligent systems with common-sense knowledge and the ability to quickly adapt to new situations is a long-standing problem in artificial intelligence.
Read More »Self-Supervised Policy Adaptation during Deployment