Continual Competitive Memory: A Neural System for Online Task-Free Lifelong Learning
This addresses the problem of lifelong learning without task guidance for AI systems, though it appears incremental as it builds on existing competitive learning principles.
The authors tackled catastrophic forgetting in online continual classification by proposing continual competitive memory (CCM), an unsupervised neural system that outperforms other competitive learning models and is competitive with state-of-the-art lifelong learning approaches on benchmarks like Split MNIST and Split NotMNIST.
In this article, we propose a novel form of unsupervised learning, continual competitive memory (CCM), as well as a computational framework to unify related neural models that operate under the principles of competition. The resulting neural system is shown to offer an effective approach for combating catastrophic forgetting in online continual classification problems. We demonstrate that the proposed CCM system not only outperforms other competitive learning neural models but also yields performance that is competitive with several modern, state-of-the-art lifelong learning approaches on benchmarks such as Split MNIST and Split NotMNIST. CCM yields a promising path forward for acquiring representations that are robust to interference from data streams, especially when the task is unknown to the model and must be inferred without external guidance.