Dynamic Machine Learning Inspired by the Visual Processing System

Innovation: Industry

Convolutional Neural Networks

Image: v2osk / Unsplash / CC BY SA - Creative Commons Attribution + ShareAlike

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

Encode/Decode

Organisms are constantly taking in new information, processing it, and storing that information as memories. Sensory information and stimuli such as sounds, smell, time, and spatial organization are encoded along with our memories. Whether we’re learning a new skill or repeating a task we’ve done before, we can easily call upon and decode that information when we need it.

Search this Function

Transduce/Convert Signals

Sometimes a signal, such as sound or vibration, reaches a living system and needs to be converted into a different, usable form. This requires converting from one type of energy form to another. For example, organisms with eyes have photoreceptors at the back of the eyes that convert light into electrical pulses. These pulses travel to the brain and allows it to register color, shape, and detail.

Search this Function

Coordinate by Self-Organization

To create and maintain a healthy community of individuals and ecosystems requires that living systems coordinate their activities. Coordination doesn’t necessarily mean that there’s a leader orchestrating what happens. In nature, coordination is usually achieved through self-organization. In a flock of geese flying in a V-formation, for example, there’s no lead goose controlling where all of the others fly. The flock uses this formation because each goose gains energy from air vortices created by the goose in front of it. The lead goose doesn’t gain that benefit, so when it tires, it moves back and another goose takes the front position.

Search this Function

Convolutional Neural Networks use a deep learning algorithm to efficiently process information.

Benefits

Increased efficiency
Increased accuracy
Decreased processing time

Applications

Artificial Intelligence
Machine learning

UN Sustainable Development Goals Addressed

Goal 9: Industry Innovation & Infrastructure

The Challenge

Computers are capable of processing a lot information faster than humans can. However, when it comes to visual information, computers slow down to process the breadth and variety of information presented in an image. The computer needs to keep track of the information, creating a lot of storage and using a lot of computing power.

Innovation Details

A Convolutional Neural Network is an algorithm that takes an input image, assigns importance to various aspects of the image, and then can differentiate between the aspects within the image, similar to the human visual processing system. The entire computer system is able to identify what is in the image because the levels of importance become features on a map that the computer recognizes. This system can then thoroughly process the entire image without creating a large amount of extra data.

The relationship between components of the visual system and the base operations of a convolutional neural network. Photo: Grace W. Lindsay/University College London.

Biological Model

The human visual system is comprised of several different types of cells. Simple cells have have ‘preferred locations’ on the image, meaning they respond most strongly to certain types of inputs (for example, a line at a particular angle). Complex cells receive input from many simple cells and thus have more spatially invariant responses. These operations are replicated in a convolutional neural network.

See Related Content

a black background with brightly colored glowing neurons and other cells in the cortex of a mouse brain

Biological Strategy

Sensing and Sharing Information

Humans

Neurons aid organisms in reacting to environmental stimuli because they collaborate to sense the environment, share information, and filter unimportant information

AskNature