Use the future to build the present
Neuromorphic Systems
Comment
Stakeholder Type
,
1Quantum Revolution& Advanced AI2HumanAugmentation3Eco-Regeneration& Geo-Engineering4Science& Diplomacy1.11.21.31.42.12.22.32.43.13.23.33.43.54.14.24.34.44.5HIGHEST ANTICIPATIONPOTENTIALAdvancedArtificial IntelligenceQuantumTechnologiesBrain-inspiredComputingBiologicalComputingCognitiveEnhancementHuman Applications of Genetic EngineeringRadical HealthExtensionConsciousnessAugmentation DecarbonisationWorldSimulationFuture FoodSystemsSpaceResourcesOceanStewardshipComplex Systems forSocial EnhancementScience-basedDiplomacyInnovationsin EducationSustainableEconomicsCollaborativeScience Diplomacy
1Quantum Revolution& Advanced AI2HumanAugmentation3Eco-Regeneration& Geo-Engineering4Science& Diplomacy1.11.21.31.42.12.22.32.43.13.23.33.43.54.14.24.34.44.5HIGHEST ANTICIPATIONPOTENTIALAdvancedArtificial IntelligenceQuantumTechnologiesBrain-inspiredComputingBiologicalComputingCognitiveEnhancementHuman Applications of Genetic EngineeringRadical HealthExtensionConsciousnessAugmentation DecarbonisationWorldSimulationFuture FoodSystemsSpaceResourcesOceanStewardshipComplex Systems forSocial EnhancementScience-basedDiplomacyInnovationsin EducationSustainableEconomicsCollaborativeScience Diplomacy

Sub-Field:

1.3.2Neuromorphic Systems

Biologically plausible artificial networks of neurons take a number of different forms in current research. A researcher's choice of approach relates to which of the biological factors they wish to mimic most strongly. Convolutional neural networks (CNN), for example, are based on the visual cortex. Spiking neural networks (SNN), based on the brain’s asynchronous processing, allow each neuron to fire independently of the others and offer a greater efficiency than synchronous networks. SNN is the architecture used by the SpiNNAker project at the University of Manchester,7 as well as by IBM (the TrueNorth chip) and Intel (the Loihi chip). There is also some interest in using photonics, rather than electronics, in neuromorphic networks.8,9 Different hardware configurations seem to provide different capabilities. Intel’s Loihi is highly configurable for specialised applications,10 for example, and IBM’s TrueNorth is particularly suited to high-speed and low-energy image processing and classification tasks.11
In addition to these mainstream efforts, there are several alternative technological approaches. Some emerging architectures involve memristors, for example, which are simple transistor-like components that have variable resistance and the ability to store multiple memory states. Several dozen AI start-ups are also developing different architectures. It is not yet clear how soon — or indeed whether — we will begin to see convergence between these efforts. To mimic the brain, all will need to find ways to efficiently integrate learning and memory in hardware elements.

Future Horizons:

×××

5-yearhorizon

Engineers finesse elements that host learning and memory

We understand how to use biologically-inspired local learning rules to learn useful tasks or form short-term memories

10-yearhorizon

Animal-like learning becomes possible

We create networks of artificial neurons and synapses that permit autonomous learning via a combination of reinforcement and self-supervised learning based on predictive models. This is supported by neuronal networks on chip, and displays adaptation, fine-tuning, and calibration, all of which co-occur through closed-loop behaviour. Autonomous systems form their own representations, make decisions and plan actions or movements based on these representations.

25-yearhorizon

Artificial mammal-like brains begin to emerge

Various experimental realisations of neuromorphic computing demonstrate memory and logic that, while still primitive compared to the naturally evolved brain, work in recognisably mammalian ways. Research replicates different capabilities of animals in technical systems, ranging from all kinds of sensors to situation awareness systems, simultaneous location and mapping, environment-independent navigation, decision-making under uncertainty, continual learning, and safe and reliable movement control.

Neuromorphic Systems - Anticipation Scores

How the experts see this field in terms of the expected time to maturity, transformational effect across science and industries, current state of awareness among stakeholders and its possible impact on people, society and the planet. See methodology for more information.

GESDA Best Reads and Key Resources