AIMC Topic: Learning

Clear Filters Showing 911 to 920 of 1476 articles

Efficient learning with augmented spikes: A case study with image classification.

Neural networks : the official journal of the International Neural Network Society
Efficient learning of spikes plays a valuable role in training spiking neural networks (SNNs) to have desired responses to input stimuli. However, current learning rules are limited to a binary form of spikes. The seemingly ubiquitous phenomenon of b...

Graph embedding clustering: Graph attention auto-encoder with cluster-specificity distribution.

Neural networks : the official journal of the International Neural Network Society
Towards exploring the topological structure of data, numerous graph embedding clustering methods have been developed in recent years, none of them takes into account the cluster-specificity distribution of the nodes representations, resulting in subo...

Against spatial-temporal discrepancy: contrastive learning-based network for surgical workflow recognition.

International journal of computer assisted radiology and surgery
PURPOSE: Automatic workflow recognition from surgical videos is fundamental and significant for developing context-aware systems in modern operating rooms. Although many approaches have been proposed to tackle challenges in this complex task, there a...

Classic Hebbian learning endows feed-forward networks with sufficient adaptability in challenging reinforcement learning tasks.

Journal of neurophysiology
A common pitfall of current reinforcement learning agents implemented in computational models is in their inadaptability postoptimization. Najarro and Risi [Najarro E, Risi S. . 2020: 20719-20731, 2020] demonstrate how such adaptability may be salvag...

Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps.

Nature communications
Cognitive maps are mental representations of spatial and conceptual relationships in an environment, and are critical for flexible behavior. To form these abstract maps, the hippocampus has to learn to separate or merge aliased observations appropria...

Augmented semantic feature based generative network for generalized zero-shot learning.

Neural networks : the official journal of the International Neural Network Society
Zero-shot learning (ZSL) aims to recognize objects in images when no training data is available for the object classes. Under generalized zero-shot learning (GZSL) setting, the test objects belong to seen or unseen categories. In many recent studies,...

Learnable Heterogeneous Convolution: Learning both topology and strength.

Neural networks : the official journal of the International Neural Network Society
Existing convolution techniques in artificial neural networks suffer from huge computation complexity, while the biological neural network works in a much more powerful yet efficient way. Inspired by the biological plasticity of dendritic topology an...

Hybrid memristor-CMOS neurons for in-situ learning in fully hardware memristive spiking neural networks.

Science bulletin
Spiking neural network, inspired by the human brain, consisting of spiking neurons and plastic synapses, is a promising solution for highly efficient data processing in neuromorphic computing. Recently, memristor-based neurons and synapses are becomi...

Autonomous learning of features for control: Experiments with embodied and situated agents.

PloS one
The efficacy of evolutionary or reinforcement learning algorithms for continuous control optimization can be enhanced by including an additional neural network dedicated to features extraction trained through self-supervision. In this paper we introd...

Adaptive SNN for Anthropomorphic Finger Control.

Sensors (Basel, Switzerland)
Anthropomorphic hands that mimic the smoothness of human hand motions should be controlled by artificial units of high biological plausibility. Adaptability is among the characteristics of such control units, which provides the anthropomorphic hand w...