Nav: Home

New learning procedure for neural networks

March 10, 2016

Rustling leaves, a creaking branch: To a mouse, these sensory impressions may at first seem harmless -- but not if a cat suddenly bursts out of the bush. If so, they were clues of impending life-threatening danger. Robert Gütig of the Max Planck Institute of Experimental Medicine in Göttingen has now found how the brain can link sensory perceptions to events occurring after a delay. In a computer model, he has developed a learning procedure in which the model neurons can learn to distinguish between many different stimuli by adjusting their activity to the frequency of the cues. The model even works when there is a time delay between the cue and the event or outcome. Not only is Gütig's learning procedure vital for the survival of every living creature in that it enables them to filter environmental stimuli; it also helps solve a number of technological learning difficulties. One possible application is in the development of speech recognition programs.

In the animal world, dangers are frequently preceded by warning signs: telltale sounds, movements and odours may be clues of an imminent attack. If a mouse survives an attack by a cat, its future will be brighter if it learns from the failed attempt and reads the clues early next time round. However, mice are constantly bombarded with a vast number of sensorial impressions, most of which are not associated with danger. So how do they know which sounds and odours from their environment presage a cat attack and which do not?

This poses a problem for the mouse's brain. In most cases, the crucial environmental stimuli are temporally dispersed from the actual attack, so the brain must link a clue and the resulting event (e.g. a sound and an attack) even though there is a delay between them. Previous theories have not provided satisfactory explanations as to how the brain bridges the gap between a cue and the associated outcome. Robert Gütig of the Max Planck Institute of Experimental Medicine has discovered how the brain can solve this problem. On the computer, he programmed a neural network that reacts to stimuli in the same way as a cluster of biological cells. This network can learn to filter out the cues that predict a subsequent event.

It depends on the frequency

The network learns by strengthening or weakening specific synapses between the model neurons. The foundation of the computer model is a synaptic learning rule under which individual neurons can increase or decrease their activity in response to a simple learning signal. Gütig has used this learning rule to establish a new learning procedure. "This 'aggregate-label' learning procedure is built on the concept of setting the connections between cells in such a way that the resulting neural activity over a certain period is proportional to the number of cues," explains Gütig. In this way, if a learning signal reflects the occurrence and intensity of certain events in the mouse's environment, the neurons learn to react to the stimuli that predict those events.

However, Gütig's networks can learn to react to environmental stimuli even when no learning signals are available in the environment. They do this by interpreting the average neural activity within a network as a learning signal. Individual neurons learn to react to stimuli that occur in the same numbers as those to which other neurons in the network react. This 'self-supervised' learning follows a principle different to the Hebbian theory that has frequently been applied in artificial neural networks. Hebbian networks learn by strengthening the synapses between neurons that spike at the same time or in quick succession. "In self-supervised learning, it is not necessary for the neural activity to be temporally aligned. The total number of spikes in a given period is the deciding factor for synaptic change," says Gütig. This means that such networks can link sensory clues of different types, e.g. visual, auditory and olfactory, even when there are significant delays between their respective neural representations.

Not only does Gütig's learning procedure explain biological processes; it could also pave the way for far-reaching improvements to technological applications such as automatic speech recognition. "That would facilitate considerable simplification of the training requirements for computer-based speech recognition. Instead of laboriously segmented language databases or complex segmentation algorithms, aggregate-label learning could manage with just the subtitles from newscasts, for example," says Gütig.
Original publication:

Robert Gütig
Spiking neurons can discover predictive features by aggregate-label learning
Science March 4, 2016; DOI: 10.1126/science.aab4113


Related Neurons Articles:

How do we get so many different types of neurons in our brain?
SMU (Southern Methodist University) researchers have discovered another layer of complexity in gene expression, which could help explain how we're able to have so many billions of neurons in our brain.
These neurons affect how much you do, or don't, want to eat
University of Arizona researchers have identified a network of neurons that coordinate with other brain regions to influence eating behaviors.
Mood neurons mature during adolescence
Researchers have discovered a mysterious group of neurons in the amygdala -- a key center for emotional processing in the brain -- that stay in an immature, prenatal developmental state throughout childhood.
Astrocytes protect neurons from toxic buildup
Neurons off-load toxic by-products to astrocytes, which process and recycle them.
Connecting neurons in the brain
Leuven researchers uncover new mechanisms of brain development that determine when, where and how strongly distinct brain cells interconnect.
The salt-craving neurons
Pass the potato chips, please! New research discovers neural circuits that regulate craving and satiation for salty tastes.
When neurons are out of shape, antidepressants may not work
Selective serotonin reuptake inhibitors (SSRIs) are the most commonly prescribed medication for major depressive disorder (MDD), yet scientists still do not understand why the treatment does not work in nearly thirty percent of patients with MDD.
Losing neurons can sometimes not be that bad
Current thinking about Alzheimer's disease is that neuronal cell death in the brain is to blame for the cognitive havoc caused by the disease.
Neurons that fire together, don't always wire together
As the adage goes 'neurons that fire together, wire together,' but a new paper published today in Neuron demonstrates that, in addition to response similarity, projection target also constrains local connectivity.
Scientists accidentally reprogram mature mouse GABA neurons into dopaminergic-like neurons
Attempting to make dopamine-producing neurons out of glial cells in mouse brains, a group of researchers instead converted mature inhibitory neurons into dopaminergic cells.
More Neurons News and Neurons Current Events

Best Science Podcasts 2019

We have hand picked the best science podcasts for 2019. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Rethinking Anger
Anger is universal and complex: it can be quiet, festering, justified, vengeful, and destructive. This hour, TED speakers explore the many sides of anger, why we need it, and who's allowed to feel it. Guests include psychologists Ryan Martin and Russell Kolts, writer Soraya Chemaly, former talk radio host Lisa Fritsch, and business professor Dan Moshavi.
Now Playing: Science for the People

#538 Nobels and Astrophysics
This week we start with this year's physics Nobel Prize awarded to Jim Peebles, Michel Mayor, and Didier Queloz and finish with a discussion of the Nobel Prizes as a way to award and highlight important science. Are they still relevant? When science breakthroughs are built on the backs of hundreds -- and sometimes thousands -- of people's hard work, how do you pick just three to highlight? Join host Rachelle Saunders and astrophysicist, author, and science communicator Ethan Siegel for their chat about astrophysics and Nobel Prizes.