devSAFARI · A Low-Power Artificial Intelligence Framework based on Vector Symbolic Architectures
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2020-01-09 → 2023-07-10
- EU contribution
- €279,192
- Participants
- 2
- Scheme
- MSCA-IF
Lines connect the coordinator with its partners.
Results in brief
A Low-Power Artificial Intelligence Framework based on Vector Symbolic Architectures
The project aims at addressing two challenges in Artificial Neural Networks (ANNs) that form the major approach to Artificial Intelligence (AI). The focus is on two AI challenges: ANNs require significant computational resources and the lack of transparency in ANNs. The project aims at addressing these challenges via the development of Hyperdimensional Computing aka Vector Symbolic Architectures (HD/VSA): a transparent, bio-inspired framework for AI with potential for implementing algorithms at low-power consumption on emerging computing hardware. In terms of the AI challenges, the overall aim is to improve the understanding of computing principles in high-dimensional spaces with HD/VSA, and to advance the theory and design principles of simple AI algorithms implementable on low-power computing hardware. This research aim comprises the following research objectives (see "MSCA_scheme.png"): O1. To evaluate the effect of using HD/VSA as a computational paradigm and prove their universality for emerging low-power computing hardware; (1st AI challenge). Implemented by work package 1; O2. To advance the capacity theory of HD/VSA and recurrent ANNs by introducing new computational approaches into the theory and expanding the theory to include methods for decoding information from HD/VSA; (2nd AI challenge). Implemented by work package 2; O3. To study the connections between ANNs and VSAs via the mathematics of high-dimensional spaces; (2nd AI challenge). Implemented by work package 2; O4. To systematize state-of-the-art methods and develop new methods for mapping data from original representations into VSAs; (VSAs Encoding problem). Implemented by work package 3; O5. To originate a novel concept of computing in superposition. Implemented by work package 3. The innovative aspect of the action is in facilitating the vision of a digital society where the obtained results provide important information supporting the design of novel intelligent devices needed to achieve this vision.
Data: CORDIS, © European Union
Project objective
Artificial Neural Networks (ANNs) form the main approach in Artificial Intelligence (AI). They have two major drawbacks, however: (1) ANNs require significant computational resources; (2) they lack transparency. These challenges restrict the widespread application of AI in daily life. The required resources prevent the use of ANNs on resource-constrained devices and the lack of transparency limits their adoption in many areas where transparency is critical. This action will address these challenges via development of Vector Symbolic Architectures (VSAs): a transparent, bio-inspired framework for AI. With respect to the 1st challenge, VSAs have the potential to become a computational paradigm for emerging low-power computing hardware with huge potential for implementing AI algorithms. With respect to the 2nd challenge, VSAs are a promising framework for opening the black box of ANNs due to their predictable statistical properties. It is expected that VSAs will allow analytical characterization of a class of Recurrent ANNs. The overall research aim of this action is to improve the understanding of computing principles in high-dimensional spaces with VSAs, and to advance the theory and design principles of simple AI algorithms implementable on emerging low-power computing hardware. The research aim comprises five research objectives. These are relevant to H2020 Work Programme since this action has much potential with respect to the “market creating innovation” and “digitising and transforming industry” aspects of the Programme. The mechanisms for achieving the objectives include both theoretical development and applied investigations. The methodological approach combines the current skills of the applicant with those acquired during this action. The applicant will develop VSAs skills to qualitatively higher level while working under the supervision of eminent researchers. This will enhance applicant’s professional maturity and prepare him for an independent career.
Original text from CORDIS.
Participants
- RISE RESEARCH INSTITUTES OF SWEDEN AB · BorasCoordinatorSweden
- THE REGENTS OF THE UNIVERSITY OF CALIFORNIA · OaklandUnited States
Links
Data: CORDIS, © European Union