Deep learning from a dynamical viewpoint

NUS mathematicians have developed a new theoretical framework based on dynamical systems to understand when and how a deep neural network can learn arbitrary relationships.

How small is a small-world network?

Discovered in the field of social sciences in the 1960s, the phenomenon known as small-world networks has fascinated popular culture and science for decades. It arose from the observation that in the world, any two people ...

Team programs a humanoid robot to communicate in sign language

For a robot to be able to "learn" sign language, it is necessary to combine different areas of engineering such as artificial intelligence, neural networks and artificial vision, as well as underactuated robotic hands. "One ...

Radar sensor module to bring added safety to autonomous driving

When a child runs out onto the road, the average human driver takes 1.6 seconds to hit the brake pedal. The reaction time is cut to 0.5 seconds for automated vehicles fitted with radar/lidar sensors and a camera system. But ...

Inhibitory neurons have two types of impact on brain oscillations

Studying the brain involves measuring the activity of billions of individual brain cells called neurons. Consequently, many brain measurement techniques produce data that is averaged to reflect the activity of large populations ...

page 10 from 14