Spike based vision platform for high-speed low power robotics
SECOND CALL
APPLICATION ID: ALL4
What we are looking for:
We are seeking innovative research proposals that explore Spiking Neural Networks (SNNs) as a viable and promising alternative to conventional AI systems.
The context:
The advancement and implementation of artificial intelligence (AI) systems are increasingly becoming resource-intensive, particularly in terms of computational power and energy consumption. This trend poses significant challenges, especially in the context of sustainable development and environmental impact.
The problem to address:
Teresa Serrano, IMSE-CSIC and Juan Andradre-IRII are joining efforts to address the problem of using Spiking Neural Networks (SNNs) as a viable and promising alternative to conventional AI systems. SNNs represent a paradigm shift in how information is processed, leveraging a sparse sequence of spikes to code information. This approach potentially offers a pathway to significantly more energy-efficient AI systems. The proposal is of interest to the various companies and organizations that support our joint activities.
Objectives:
- To investigate the potential of SNNs in reducing the energy consumption of AI systems without compromising their performance.
- To develop models or prototypes that demonstrate the practical application of SNNs in various AI scenarios.
Qualifications:
-
Indispensable: PhD in robotics, computer vision, AI or related area.
-
Experience with Bayesian state estimation, machine learning, deep learning, spiking neural networks.
-
Experience with geometrical computer vision, sensor fusion.
-
Experience with event cameras.
Expected Outcomes:
- Innovative solutions or prototypes employing SNNs in practical AI applications.
- Contributions to the body of knowledge in [energy-efficient AI computing, potentially guiding future research and development in the field.] – this is a fixed objective
