Adaptive cognition implemented with a context-aware and flexible neuron for next-generation artificial intelligence

TL;DR

This paper introduces a novel hardware-based adaptive neuron using magnetic skyrmions that mimics brain-like adaptive cognitive abilities, enabling more efficient and accurate artificial intelligence applications such as cancer diagnosis.

Contribution

The work presents a new adaptive oscillatory neuron design that demonstrates context-awareness, cross-frequency coupling, and feature binding in hardware, advancing neuromorphic computing capabilities.

Findings

Demonstrated hardware neurons with context-awareness and cross-frequency coupling.

Achieved higher accuracy and faster learning in cancer diagnosis with adaptive neural networks.

Showed improved energy efficiency and compactness over traditional non-adaptive ANNs.

Abstract

Neuromorphic computing mimics the organizational principles of the brain in its quest to replicate the brain's intellectual abilities. An impressive ability of the brain is its adaptive intelligence, which allows the brain to regulate its functions "on the fly" to cope with myriad and ever-changing situations. In particular, the brain displays three adaptive and advanced intelligence abilities of context-awareness, cross frequency coupling and feature binding. To mimic these adaptive cognitive abilities, we design and simulate a novel, hardware-based adaptive oscillatory neuron using a lattice of magnetic skyrmions. Charge current fed to the neuron reconfigures the skyrmion lattice, thereby modulating the neuron's state, its dynamics and its transfer function "on the fly". This adaptive neuron is used to demonstrate the three cognitive abilities, of which context-awareness and cross-frequency coupling have not been previously realized in hardware neurons. Additionally, the neuron is used to construct an adaptive artificial neural network (ANN) and perform context-aware diagnosis of breast cancer. Simulations show that the adaptive ANN diagnoses cancer with higher accuracy while learning faster from smaller amounts of data and using a more compact and energy-efficient network than the state-of-the-art non-adaptive ANNs used for cancer diagnosis. The work further describes how hardware-based adaptive neurons can mitigate several critical challenges facing contemporary ANNs. Modern ANNs require large amounts of training data, energy and chip area and are highly task-specific; conversely, hardware-based ANNs built with adaptive neurons show faster learning from smaller datasets, compact architectures, energy-efficiency, fault-tolerance and can lead to the realization of general artificial intelligence.