On-chip Few-shot Learning with Surrogate Gradient Descent on a Neuromorphic Processor

This live demonstration will show real-time, embedded learning of gestures shown to a dynamics vision sensor in neuromorphic hardware. A multi-layer spiking neural network implemented in the Loihi neuromorphic processor partially trained on 11 classes of gestures will be able to learn new classes of gestures shown to the vision sensor by using a combination of transfer learning and local synaptic plasticity. Visitors will experience real-time learning of new classes of gestures they show to the vision sensor whose data is processed in real-time by the network on a connected neuromorphic chip.

[1]  James L. McClelland,et al.  Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. , 1995, Psychological review.

[2]  W. Schultz.  Getting Formal with Dopamine and Reward , 2002, Neuron.

[3]  Gert Cauwenberghs,et al.  Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning , 2017, Front. Neurosci..

[4]  Hong Wang,et al.  Loihi: A Neuromorphic Manycore Processor with On-Chip Learning , 2018, IEEE Micro.

[5]  W. Senn,et al.  Learning by the Dendritic Prediction of Somatic Spiking , 2014, Neuron.

[6]  Garrick Orchard,et al.  SLAYER: Spike Layer Error Reassignment in Time , 2018, NeurIPS.

[7]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[8]  Tobi Delbruck,et al.  A 240 × 180 130 dB 3 µs Latency Global Shutter Spatiotemporal Vision Sensor , 2014, IEEE Journal of Solid-State Circuits.

[9]  Emre Neftci,et al.  Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-based optimization to spiking neural networks , 2019, IEEE Signal Processing Magazine.

[10]  Surya Ganguli,et al.  SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks , 2017, Neural Computation.

[11]  Somnath Paul,et al.  Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines , 2016, Front. Neurosci..

[12]  Tobi Delbrück,et al.  A Low Power, Fully Event-Based Gesture Recognition System , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[14]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[15]  Jean-Pascal Pfister,et al.  Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning , 2005, Neural Computation.

[16]  Stefano Fusi,et al.  Computational principles of biological memory , 2015, 1507.07580.

[17]  Wulfram Gerstner,et al.  Neuronal Dynamics: From Single Neurons To Networks And Models Of Cognition , 2014 .

[18]  Emre O. Neftci,et al.  Data and Power Efficient Intelligence with Neuromorphic Learning Machines , 2018, iScience.