The Science of Adaptive Intelligence: A Multidisciplinary Exploration
We look for the unifying principles of efficiency and cost through the lens of hierarchies and self-organization principles, at a function level and at a structural level, translating them into mathematical rules that apply to the construction of more ethical algorithms. Specifically, we:
- Investigate the neural and computational principles of developmental cognition and other living systems that are suitable for this sort of exploration
- Explore the evolution of cognitive architectures and their application in AI and robotics
- Develop new frameworks for understanding complex adaptive systems
- Bridge gaps between human and machine intelligence through innovative modelling and experimentation
A recent research published in Frontiers in Artificial Intelligence showed that
“The human brain, a marvel of biological engineering, operates at an astonishingly low power consumption of about 12 watts, roughly equivalent to a dim light bulb. This efficiency stems from its highly optimized neural architecture, developed over millions of years of evolution.
In contrast, current AI systems, such as large-scale neural networks, often require massive computational resources, consuming up to 2.7 billion watts in large data centers. This inefficiency arises from the digital nature of AI, which relies on silicon-based processors and vast arrays of GPUs or TPUs. These systems perform billions of matrix operations, requiring significant electrical power for computation, cooling, and data transfer.”
https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2023.1240653/full
Cognitive Neuroscience: The Architecture of Thought
Understanding the human mind requires unraveling the neural mechanisms that underlie perception, learning, and decision-making, stage-by-stage. A stage-like approach is foundational to us. It enables the process of quantifying and designing self-organizing complex structures. We investigate how hierarchical processing and distributed networks enable intelligence, from low-level sensory processing to high-level cognition.
Complex Systems: The Dynamics of Adaptation
We are curious about not only how to mimic learning, but how to discriminate the processes of learning and development so as to mimic development and evolution itself, with reverence to biological plausibility. It is in this discrimination process that the importance of self-organization, non-linear dynamics, and emergent properties appear as foundational.
Robotics and Artificial Cognition: Bridging Biology and Technology
How can artificial systems replicate the flexibility and adaptability of human intelligence? Our work in robotics and computational cognition explores biologically inspired models that integrate and discriminate learning and developmental processes, exploring the boundaries of artificial systems in what concerns autonomy and self-development.
Human Development and Evolution: Intelligence Across Time
To fully understand the complexity of living systems, we must trace its origins. We explore how evolutionary pressures and developmental processes shape adaptive behavior and adaptable structure and function, offering insights into both natural and artificial processes, dynamics, functions, and architectures.
By integrating these perspectives, Self-Stacked-Systems Collaborative Research Group seeks to unravel the deep mechanisms of adaptive intelligence, in a multi-disciplinary and multi-scale perspective.