Publish at May 24 2023 Updated May 24 2023
"Machine learning is one of the leading methods in artificial intelligence. At the forefront of unsupervised learning techniques, the Modal project-team is working on innovative approaches, exploiting data represented in graphs."
The Modal team uses the capabilities of digital tools to analyze complex data and make the information they contain intelligible - a task that is far beyond human comprehension, given the sheer quantity and diversity of data! Think of the millions of business transactions or disparate data transmitted over a network. The relationships between data types and various location, time or even other parameters such as the weather, inventory status or a national holiday, all of which are continuous or sporadic relationships are unstructured and often even unidentified data.
These data modeled in graphs (which can be multi-dimensional) allow for the detection of relationships that are virtually invisible in other forms and, more importantly, with far fewer computational and energy resources.
For example, in business, when demand for a product exceeds supply, demand for substitute products will increase. Knowing which way to look can be of great value to both a producer and a supplier, but initially it is not information written down anywhere.
Examples of this order are numerous...
For the full article: Another artificial intelligence with graph-based learning
Illustration: Pixabay - Geralt
Domaine de Voluceau
Rocquencourt - B.P. 105
78153 Le Chesnay
France
Tél.: 33 (0)1 39 63 55 11
Access exclusive services for free
Subscribe and receive newsletters on:
In addition, index your favorite resources in your own folders and find your history of consultation.
Subscribe to the newsletterYou might also like:
A mathematical model to reduce the polarization of opinions
The results of Frank Valencia and his team already show that social networks can be designed differently, by adjusting the algorithms according to the biases that will impact the flow of influence and thus produce different results, with less polarization.
Present security compromised by the future: at the dawn of quantum computers
A race is on between the developers of quantum computers and cryptographers who seek to ensure data confidentiality because the most advanced current protocols in cryptography are challenged by the capabilities of quantum computers.
The wonderful world of intelligent algorithm bias control
The biases that algorithms can develop are known and numerous. While everyone recognizes the need for regulation, the challenge of drafting enforceable and effective regulations is on the table. The Regalia pilot project is trying to devise ways.
Materials that obey their designer: microstructural design
By simply orienting material structures, directional and orientable properties can be obtained.
Follow the evolution of the algorithms
"The tremendous computational power that quantum computing offers requires a rethinking of high performance computing (HPC) algorithms."
