Summary
Artificial neural networks (ANNs) have found applications in a wide variety of real-world problems. Despite this tremendous success, artificial intelligence systems still face major challenges due to their reliance on extensive training and large datasets. Recent reports indicate that the architecture of ANNs could be a prime target for reducing their training and data requirements.
We hypothesize that such architectural features can be identified from neuronal networks in the brain, which have evolved to efficiently perform highly specialized functions. Recent advances in electron microscopy will soon provide detailed reconstructions of large-scale neuronal networks from different brain areas, species, developmental stages and/or pathological conditions. However, even if such data become available, directly transforming neuronal network reconstructions into ANNs will raise problems of interpretability, due to their enormous complexity, and generalizability, due to high inter-individual variability.
Here, we will resolve these challenges by implementing a set of computational approaches that allow the extraction of rules that explain the wiring properties underlying dense connectomics data, the transfer of these anatomical principles into the design of ANN architectures, and the evaluation of how these principles impact performance on a battery of deep learning tasks. This unique methodology will lay the foundation for groundbreaking insights into how different network architectures facilitate specific brain functions, and also how the underlying anatomical principles can inform the development of more effective and efficient artificial intelligence systems.
Our methodology will be publicly accessible online to scientists, but also to companies and non-profit organizations that seek to improve the performance or reduce training data requirements for applications of deep learning.
We hypothesize that such architectural features can be identified from neuronal networks in the brain, which have evolved to efficiently perform highly specialized functions. Recent advances in electron microscopy will soon provide detailed reconstructions of large-scale neuronal networks from different brain areas, species, developmental stages and/or pathological conditions. However, even if such data become available, directly transforming neuronal network reconstructions into ANNs will raise problems of interpretability, due to their enormous complexity, and generalizability, due to high inter-individual variability.
Here, we will resolve these challenges by implementing a set of computational approaches that allow the extraction of rules that explain the wiring properties underlying dense connectomics data, the transfer of these anatomical principles into the design of ANN architectures, and the evaluation of how these principles impact performance on a battery of deep learning tasks. This unique methodology will lay the foundation for groundbreaking insights into how different network architectures facilitate specific brain functions, and also how the underlying anatomical principles can inform the development of more effective and efficient artificial intelligence systems.
Our methodology will be publicly accessible online to scientists, but also to companies and non-profit organizations that seek to improve the performance or reduce training data requirements for applications of deep learning.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101069192 |
| Start date: | 01-07-2022 |
| End date: | 31-12-2023 |
| Total budget - Public funding: | - 150 000,00 Euro |
Cordis data
Original description
Artificial neural networks (ANNs) have found applications in a wide variety of real-world problems. Despite this tremendous success, artificial intelligence systems still face major challenges due to their reliance on extensive training and large datasets. Recent reports indicate that the architecture of ANNs could be a prime target for reducing their training and data requirements.We hypothesize that such architectural features can be identified from neuronal networks in the brain, which have evolved to efficiently perform highly specialized functions. Recent advances in electron microscopy will soon provide detailed reconstructions of large-scale neuronal networks from different brain areas, species, developmental stages and/or pathological conditions. However, even if such data become available, directly transforming neuronal network reconstructions into ANNs will raise problems of interpretability, due to their enormous complexity, and generalizability, due to high inter-individual variability.
Here, we will resolve these challenges by implementing a set of computational approaches that allow the extraction of rules that explain the wiring properties underlying dense connectomics data, the transfer of these anatomical principles into the design of ANN architectures, and the evaluation of how these principles impact performance on a battery of deep learning tasks. This unique methodology will lay the foundation for groundbreaking insights into how different network architectures facilitate specific brain functions, and also how the underlying anatomical principles can inform the development of more effective and efficient artificial intelligence systems.
Our methodology will be publicly accessible online to scientists, but also to companies and non-profit organizations that seek to improve the performance or reduce training data requirements for applications of deep learning.
Status
SIGNEDCall topic
ERC-2022-POC1Update Date
09-02-2023
Geographical location(s)
Structured mapping
