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
- Brain-inspired replay for continual learning with artificial neural networkson August 13, 2020 at 2:14 am
One challenge that faces artificial intelligence is the inability of deep neural networks to continuously learn new information without catastrophically forgetting what has been learnt before. To ...
- A comparative analysis of artificial neural networks and wavelet hybrid approaches to long-term toxic heavy metal predictionon August 10, 2020 at 2:10 am
The occurrence of toxic metals in the aquatic environment is as caused by a variety of contaminations which makes difficulty in the concentration prediction. In this study, conventional methods of ...
- Neural-Network Compiler Adds a Glow to Microson August 7, 2020 at 9:29 am
To give a boost to machine-learning functionality in its MCUs and DSPs, NXP incorporated the open-source Glow neural-network compiler to the technology mix.
- New neural network helps doctors explain relapses of heart failure patientson August 7, 2020 at 9:27 am
Patient data are a treasure trove for AI researchers. There's a problem though: many algorithms used to mine patient data act as black boxes, which makes their predictions often hard to interpret for ...
- Neural Network Software Market 2020: key Vendors, Trends, Analysis, Segmentation, Forecast to 2025on August 6, 2020 at 4:42 pm
The Neural Network Software Market is expected to be around US$ 53 Billion by 2025 at a CAGR of 33% in the given forecast period. You will get latest updated report as per the COVID-19 Impact on this ...
- Training neural circuits early in development improves response, study findson August 6, 2020 at 12:36 pm
When it comes to training neural circuits for tissue engineering or biomedical applications, a new study suggests a key parameter: Train them young. Training of engineered neurons has many ...
- Deep learning on cell signaling networks establishes AI for single-cell biologyon August 4, 2020 at 8:45 am
Computer systems that emulate key aspects of human problem solving are commonly referred to as artificial intelligence (AI). This field has seen massive progress over the last years. Most notably, ...
- Neural Networks Need Naps, Just Like Youon August 3, 2020 at 6:09 am
Researchers at Los Alamos National Laboratory have discovered that neural networks benefit from periods of downtime, just like humans need a good night's r ...
- Neural Networks Need Naps, Just Like Youon August 3, 2020 at 5:53 am
Researchers at Los Alamos National Laboratory have discovered that neural networks benefit from periods of downtime, just like humans need a good night's rest. After long periods of work, a neural net ...
- How Artificial Neural Networks Paved the Way For A Dramatic New Theory of Dreamson July 31, 2020 at 8:15 am
Machine learning experts struggle to deal with "overfitting" in neural networks. Evolution solved it with dreams, says new theory.
via Bing News