DeepMind’s Psychlab uses psychology to understand AI behaviors
We have seen a few examples of rogue artificial intelligence in the last few years, from the Facebook AI that invented its own language to Microsoft Corp.’s surprisingly racist chatbot. It is not always easy to understand why an AI does the things it does, but Google LLC’s DeepMind believes it has come up with a solution to this problem: psychology.
DeepMind announced today that it has released Psychlab, an open-source AI platform that studies AI behaviors in much the same way that psychologists study human behaviors.
Psychlab is built on DeepMind Lab, which uses simulated 3D environments to train and test AI in different spatial tasks. These environments allow Psychlab to recreate real-world psychology experiments, with AI agents acting as the main test subjects.
“This usually consists of a participant sitting in front of a computer monitor using a mouse to respond to the onscreen task,” DeepMind researcher Joel Leibo explained in a blog post. “Similarly, our environment allows a virtual subject to perform tasks on a virtual computer monitor, using the direction of its gaze to respond. This allows humans and artificial agents to both take the same tests, minimizing experimental differences. It also makes it easier to connect with the existing literature in cognitive psychology and draw insights from it.”
DeepMind has released eight classic psychology experiments for Psychlab that test different cognitive abilities. These experiments include (via deepmind.com):
- Visual search–tests ability to search an array of items for a target (pictured).
- Continuous recognition–tests memory for a growing list of items.
- Arbitrary visuomotor mapping–tests recall of stimulus-response pairings.
- Change detection–tests ability to detect changes in an array of objects reappearing after a delay.
- Visual acuity and contrast sensitivity–tests ability to identify small and low-contrast stimuli.
- Glass pattern detection–tests global form perception.
- Random dot motion discrimination–tests ability to perceive coherent motion.
- Multiple object tracking–tests ability to track moving objects over time.
Leibo said Psychlab has “a flexible and easy-to-learn API” that will allow researchers to create and share their own experiments. DeepMind has also released Psychlab’s source code, and Leibo explained that the company hopes that “the wider research community will make use of it in their own research and help us shape it going forward .”
Here’s a video of a visual search task on Psychlab:
Photo: A Health Blog via photopin cc
A message from John Furrier, co-founder of SiliconANGLE:
Your vote of support is important to us and it helps us keep the content FREE.
One click below supports our mission to provide free, deep, and relevant content.
Join our community on YouTube
Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.
THANK YOU