paper-with-me

홈 › Papers

TACOS: Task Agnostic Continual Learning in Spiking Neural Networks

2024-08-16 · Nicholas Soures, Peter Helfer, Anurag Daram, Tej Pandit, Dhireesha Kudithipudi

Catastrophic interference, the loss of previously learned information when learning new information, remains a major challenge in machine learning. Since living organisms do not seem to suffer from this problem, researchers have taken inspiration from biology to improve memory retention in artificial intelligence systems. However, previous attempts to use bio-inspired mechanisms have typically resulted in systems that rely on task boundary information during training and/or explicit task identification during inference, information that is not available in real-world scenarios. Here, we show that neuro-inspired mechanisms such as synaptic consolidation and metaplasticity can mitigate catastrophic interference in a spiking neural network, using only synapse-local information, with no need for task awareness, and with a fixed memory size that does not need to be increased when training on new tasks. Our model, TACOS, combines neuromodulation with complex synaptic dynamics to enable new learning while protecting previous information. We evaluate TACOS on sequential image recognition tasks and demonstrate its effectiveness in reducing catastrophic interference. Our results show that TACOS outperforms existing regularization techniques in domain-incremental learning scenarios. We also report the results of an ablation study to elucidate the contribution of each neuro-inspired mechanism separately.

📄 PDF Abstract BibTeX arXiv:2409.00021

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningIncremental Learning

Similar Papers 제목 키워드 기반

TACOS: Task Agnostic COordinator of a multi-drone System

2025-10-02 · Alessandro Nazzari, Roberto Rubinacci, Marco Lovera arxiv

When a single pilot is responsible for managing a multi-drone system, the task may demand varying levels of autonomy, from direct control of individual UAVs, to group-level coordination, to fully autonomous swarm behavio…

Towards Improved Imbalance Robustness in Continual Multi-Label Learning with Dual Output Spiking Architecture (DOSA)

2024-02-07 · Sourav Mishra, Shirin Dora, Suresh Sundaram

Algorithms designed for addressing typical supervised classification problems can only learn from a fixed set of samples and labels, making them unsuitable for the real world, where data arrives as a stream of samples of…

Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label Learning

Genesis: A Spiking Neuromorphic Accelerator With On-chip Continual Learning

2025-09-06 · Vedant Karia, Abdullah Zyarah, Dhireesha Kudithipudi arxiv

Continual learning, the ability to acquire and transfer knowledge through a models lifetime, is critical for artificial agents that interact in real-world environments. Biological brains inherently demonstrate these capa…

Continual Learning

Enhancing Efficient Continual Learning with Dynamic Structure Development of Spiking Neural Networks

2023-08-09 · Bing Han, Feifei Zhao, Yi Zeng, Wenxuan Pan 외

Children possess the ability to learn multiple cognitive tasks sequentially, which is a major challenge toward the long-term goal of artificial general intelligence. Existing continual learning frameworks are usually app…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning

Similarity-based context aware continual learning for spiking neural networks

2024-10-28 · Bing Han, Feifei Zhao, Yang Li, Qingqun Kong 외

Biological brains have the capability to adaptively coordinate relevant neuronal populations based on the task context to learn continuously changing tasks in real-world environments. However, existing spiking neural net…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning