Neural networks learn to link temporally dispersed stimuli
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.
Learn more: New learning procedure for neural networks
The Latest on: Neural networks
via Google News
The Latest on: Neural networks
- AI companion Replika is supporting humans' emotional needs with their artificial neural networks and thoughtfully scripted dialogueson May 15, 2022 at 8:13 am
This friendly bot converses with you about your family, health, emotions, aspirations, job, hobbies, holidays et al ...
- ITMO: ITMO Scientists Train Neural Networks to Determine Solution Concentration Via Air Bubbleson May 13, 2022 at 9:52 pm
Not all bubbles are goodProbably everyone has seen bubbles that form along the walls of a water bottle when it is left undisturbed for a while. This phenomenon is best observed in soda. The thing is, ...
- Effects of stress on adolescent brain's 'triple network'on May 11, 2022 at 9:44 am
Stress and trauma during adolescence can lead to long-term health consequences such as psychiatric disorders, which may arise from neurodevelopmental effects on brain circuitry. A new study in ...
- Researchers Build Neural Networks With Actual Neuronson May 10, 2022 at 5:00 pm
Neural networks have become a hot topic over the last decade, put to work on jobs from recognizing image content to generating text and even playing video games. However, these artificial neural ...
- Using graph neural networks to measure the spatial homogeneity of road networkson May 9, 2022 at 6:30 am
Researchers at Purdue University and Peking University have recently carried out a study aimed at better understanding road networks in cities worldwide using machine-learning tools. Their paper, ...
- Researchers discover a bi-directional neural network connecting the legs and visual system to shape walkingon May 8, 2022 at 7:58 am
A fruit fly walks on a small styrofoam ball fashioned into a floating 3D treadmill. The room is completely dark, and yet, an electrode recording visual neurons in the fly's brain relays a mysterious ...
- deep neural networkson May 6, 2022 at 5:00 pm
Prosthetic limbs have been slow to evolve from simple motionless replicas of human body parts to moving, active devices. A major part of this is that controlling the many joints of a prosthetic is ...
- Newly discovered neural network gets visual and motor circuits in syncon May 6, 2022 at 8:00 am
A fruit fly walks on a small styrofoam ball fashioned into a floating 3D treadmill. The room is completely dark, and yet, an electrode recording visual neurons in the fly's brain relays a mysterious ...
- New Neural Processors Address Emerging Neural Networkson May 5, 2022 at 12:04 am
It’s been ten years since AlexNet, a deep learning convolutional neural network (CNN) model running on GPUs, displaced more traditional vision processing algorithms to win the ImageNet Large Scale ...
- Trained neural network pipeline simulates physical systems of rigid and deformable bodies and environmental conditionson May 3, 2022 at 7:07 am
As this can be a complex and costly process—often requiring markers placed on objects or people and recording the action sequence—researchers are working to shift the burden to neural networks, which ...
via Bing News