4089. Efficient online algorithms for Artificial Intelligence
Invited abstract in session OR conjectures for AI, stream OR and Ethics, and Societal Perspectives.
Authors (first author is the speaker)
| 1. | Leonidas Sakalauskas
|
| Vytautas Magnus University |
Abstract
The technological revolution of inexpensive chips is a decisive factor in the modern economic and social development (Leiserson et al, 2020). The mathematical foundation for the most widespread AI neural network technology is laid by the Kolmogorov-Vitushkin theorems.
The paper highlights the conjecture of efficient training online training and discusses its partial solution when solving control problems of stochastic dynamic systems. Other relevant aspects of applied mathematical modeling are discussed as well.
Keywords
- Stochastic Optimization
- Behavioural Operational Research
- Artificial Intelligence
Status: accepted
Back to the list of papers