Search for: All records

Incremental learning is a challenging task in the field of machine learning, and it is a key step towards autonomous learning and adaptation. With the increasing attention on neuromorphic computing, there is an urgent need to investigate incremental learning techniques that can work in this paradigm to maintain energy efficiency while benefiting from flexibility and adaptability. In this paper, we present SEMINAR (sensitivity modulated importance networking and rehearsal), an incremental learning algorithm designed specifically for EMSTDP (Error Modulated Synaptic-Timing Dependent Plasticity), which performs supervised learning for multi-layer spiking neural networks (SNN) implemented on neuromorphic hardware, such as Loihi. SEMINAR uses critical synapse selection, differential learning rate and a replay buffer to enable the model to retain past knowledge while maintaining flexibility to learn new tasks. Our experimental results show that, when combined with the EMSTDP, SEMINAR outperforms different baseline incremental learning algorithms and gives more than 4% improvement on several widely used datasets such as Split-MNIST, Split-Fashion MNIST, Split-NMNIST and MSTAR. 

Spiking neural networks(SNNs) have drawn broad research interests in recent years due to their high energy efficiency and biologically-plausibility. They have proven to be competitive in many machine learning tasks. Similar to all Artificial Neural Network(ANNs) machine learning models, the SNNs rely on the assumption that the training and testing data are drawn from the same distribution. As the environment changes gradually, the input distribution will shift over time, and the performance of SNNs turns out to be brittle. To this end, we propose a unified framework that can adapt nonstationary streaming data by exploiting unlabeled intermediate domain, and fits with the in-hardware SNN learning algorithm Error-modulated STDP. Specifically, we propose a unique self training framework to generate pseudo labels to retrain the model for intermediate and target domains. In addition, we develop an online-normalization method with an auxiliary neuron to normalize the output of the hidden layers. By combining the normalization with self-training, our approach gains average classification improvements over 10% on MNIST, NMINST, and two other datasets.