The importance of space and time in neuromorphic cognitive agents
This addresses the problem of high energy consumption and lack of agility in AI systems for applications like robotics and autonomous systems, but it is incremental as it builds on existing neuromorphic concepts.
The paper tackles the efficiency and adaptivity gap between biological neural systems and artificial neural networks by presenting neuromorphic processing devices that emulate biological in-memory computing and continuous-time dynamics, showing advantages in computational efficiency and examples of autonomous learning in embodied agents.
Artificial neural networks and computational neuroscience models have made tremendous progress, allowing computers to achieve impressive results in artificial intelligence (AI) applications, such as image recognition, natural language processing, or autonomous driving. Despite this remarkable progress, biological neural systems consume orders of magnitude less energy than today's artificial neural networks and are much more agile and adaptive. This efficiency and adaptivity gap is partially explained by the computing substrate of biological neural processing systems that is fundamentally different from the way today's computers are built. Biological systems use in-memory computing elements operating in a massively parallel way rather than time-multiplexed computing units that are reused in a sequential fashion. Moreover, activity of biological neurons follows continuous-time dynamics in real, physical time, instead of operating on discrete temporal cycles abstracted away from real-time. Here, we present neuromorphic processing devices that emulate the biological style of processing by using parallel instances of mixed-signal analog/digital circuits that operate in real time. We argue that this approach brings significant advantages in efficiency of computation. We show examples of embodied neuromorphic agents that use such devices to interact with the environment and exhibit autonomous learning.