IEEE Journal on Exploratory Solid-State Computational Devices and Circuits · 2019 · 41 citations · 24 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningSynaptic PlasticityContinual LearningDeep LearningLearning In Neural SystemsNeural NetworksNeural PlasticitySpike-timing-dependent PlasticityCatastrophic ForgettingConvolutional Neural NetworksMultilayer PerceptronNeural Network ModelingPerceptronPhase-change MemoryRedundancy DesignSpike-timing Plasticity
Continual learning is the ability to acquire a new task or knowledge without losing any previously collected information. Achieving continual learning in artificial intelligence (AI) is currently prevented by catastrophic forgetting, where training of a new task deletes all previously learned tasks. Here, we present a new concept of a neural network capable of combining supervised convolutional learning with bio-inspired unsupervised learning. Brain-inspired concepts such as spike-timing-dependent plasticity (STDP) and neural redundancy are shown to enable continual learning and prevent catastrophic forgetting without compromising standard accuracy achievable with state-of-the-art neural networks. Unsupervised learning by STDP is demonstrated by hardware experiments with a one-layer perceptron adopting phase-change memory (PCM) synapses. Finally, we demonstrate full testing classification of Modified National Institute of Standards and Technology (MNIST) database with an accuracy of 98% and continual learning of up to 30% non-trained classes with 83% average accuracy.
24
Face recognition: a convolutional neural-network approach
Sandra Lawrence, C. Lee Giles, Ah Chung Tsoi et al. · IEEE Transactions on Neural Networks · 1997 · 3.1K citations