Scaling of Hardware-Compatible Perturbative Training Algorithms

Engineering, Electrical Engineering, Information Science, Electronic Information, Computer Science, Artificial Intelligence,
perturbative training   hardware compatibility   gradient estimation   stochastic gradient descent   neuromorphic hardware   machine learning   computational efficiency  

With the rapid development of artificial intelligence (AI) technology, artificial neural networks (ANNs) have achieved significant success in multiple fields. However, traditional neural network training methods—especially the backpropagation algorithm—face numerous challenges in hardware implementation. Although the backpropagation algorithm is ef...

Resistive Memory-Based Zero-Shot Liquid State Machine for Multimodal Event Data Learning

Information Science, Electronic Information, Computer Science, Artificial Intelligence,
resistive memory   zero-shot learning   liquid state machine   multimodal data   neuromorphic hardware   event-driven learning   brain-inspired computing  

Novel Resistive Memory-Driven Zero-Shot Multimodal Event Learning System: A Report on Hardware-Software Co-Design Academic Background The human brain is a complex spiking neural network (SNN) capable of zero-shot learning in multimodal signals with minimal power consumption, allowing generalization of existing knowledge to address new tasks. Howeve...

Learning Inverse Kinematics Using Neural Computational Primitives on Neuromorphic Hardware

Engineering, Electrical Engineering, Information Science, Electronic Information, Automation, Artificial Intelligence, Life Sciences, Bioengineering,
inverse kinematics   neural computation   neuromorphic hardware   motor control   spiking neural network  

Learning Inverse Dynamics Using Brain-Inspired Computational Principles on Neuromorphic Hardware Background and Research Motivation In the modern field of robotics, there is great potential for low-latency neuromorphic processing systems enabling autonomous artificial agents. However, the variability and low precision of current hardware foundation...