Adept Artificial Intelligence Software Inspired by Humans

Innovation: Academia

MIT & Georgetown University

2021

Image: Jukan Tateisi / Unsplash / CC BY SA - Creative Commons Attribution + ShareAlike

Send Electrical/Magnetic Signals

Some living systems send electric or magnetic signals, often as a way of communicating with other living systems or sensing their environment. Electric and magnetic signaling requires specialized organs, and thus appear to be less common than other types of signals, such as audible and visual ones. Electric fish produce very sophisticated electric signals that not only help them find mates, but are also sensitive enough to enable them to distinguish individual fish.

Search this Function

Sense Light (Visible Spectrum) From the Environment

Living systems constantly receive signals from their environment that help them survive. Light (in the visible spectrum) can come from other living systems (such as fireflies) or from non-living sources (such as the sun). Survival often depends on sensing and responding to challenges like low light conditions or light that has been altered in some way. Because basic survival is at stake, living systems must excel at meeting those challenges. A well-known phenomenon is how water bends light. A stork trying to catch a fish underwater can compensate for this bending effect so that when it strikes at the fish, it has a good chance of catching it.

Search this Function

Learn

Living systems obtain information from their environment and use it to find mates and resources, and to escape threats. Some reactions to gathered information are instinctual or innate behaviors, not based on previous experiences. But other reactions are based on previous experiences, which means that, at some level, the living system is learning. Learning can involve a living system passing information to another living system, or a living system obtaining information and using it in a feedback loop. That information can include knowledge, experience, behavior, and skills. Learning takes place when information that is new to the recipient is used to modify existing behavior or skills. The making and use of tools by some species of birds and mammals is a learned behavior. If a chimpanzee uses a stick to successfully get ants out of an ant mound and continues to do so, it has learned that behavior. If another chimpanzee observes this technique and replicates it, it has learned from the first chimp.

Search this Function

Compute

Computation allows an organism to take in and process information to make decisions. Whether it be calculating how fast prey is moving or deciding where to build a nest, computation is an important part of an organism’s life.

Search this Function

Artificial intelligence software from MIT and Georgetown University Medical Center uses prior learning to more efficiently understand visual concepts.

Benefits

Increased speed
Increased efficiency
Dynamic

Applications

AI/Machine Learning

UN Sustainable Development Goals Addressed

Goal 9: Industry Innovation & Infrastructure

The Challenge

Humans have the ability to quickly and accurately learn new visual concepts without a lot of data, oftentimes from just a single example. Even toddlers can learn to quickly recognize zebras and distinguish them from cats, horses, and giraffes. This is because the brain is able to simplify learning by using previously learned representations to inform new information. Computers, however, oftentimes need to see an example hundreds or even thousands of times to learn what it is and distinguish it from a similar object.

Innovation Details

The AI (artificial intelligence) software allows computers to learn new visual concepts with only a small number of examples, similar to how the brain learns. It does this by identifying relationships between visual categories to differentiate visual data, rather than just identifying single characteristics such as color and shape. For example, rather than identifying the basic visual features of a platypus, it stores more high-level concepts, like how a platypus looks a bit like a duck, a beaver, and a sea otter. The computer then stores this information in a databank that can be easily referenced and associated with new, incoming information. Altogether, this increases the efficiency and speed of visual learning in computers.

Biological Model

As the brain learns, it builds networks of connected neurons to store and share information including, size, color, and texture of an object. One area of the brain, the anterior temporal lobe, is thought to contain complex neural hierarchies that code for additional “abstract” concept representations that go beyond the basic characteristics of color and shape. This ‘database’ of information is constantly being updated and referenced whenever we learn a new task or object. This allows humans to learn new information much more quickly and easily.

References

Journal article

Leveraging Prior Concept Learning Improves Generalization From Few Examples in Computational Models of Human Object Recognition

embedly preview

AskNature