Adithya Gurunathan
ABSTRACT
Biologically plausible learning is of interest not only to neuroscientists but also to the neuromorphic community due to local learning rules, and the promise of efficient hardware implementations. Spike timing dependent plasticity is the conventional biologically plausible learning rule that has been used to train SNNs. However, due to its advantages, spike driven synaptic plasticity (SDSP) rule has begun to be used in some implementations. Unlike STDP, however, under some parameter settings, we note that learning is not proportional to the incoming input received by an output neuron. This phenomenon leads to false positive learning, or otherwise spurious learning. In this paper, we first present a simple 5-class network that gets 99.97% accuracy on simple patterns. Then we present a detailed examination of spurious learning in SDSP networks.
- J. M. Brader, W. Senn, and S. Fusi. 2007. Learning real-world stimuli in a neural network with spike-driven synaptic dynamics. Neural Computation 19(2007), 2881–2912.Google Scholar
Digital Library
- P. U. Diehl and M. Cook. 2015. Unsupervised learning of digit recognition using spike-timing dependent plasticity. Front. Comp. Neurosci(2015). https://doi.org/10.3389/fncom.2015.00099Google Scholar
- C. Frenkel, G. Indiveri, J. D. Legat, and D. Bol. 2017. A fully-synthesized 20-gate digital spike-based synapse with embedded online learning. In Proc. IEEE Int. Symp. Circuits Syst.Baltimore, MD. https://doi.org/10.1109/ISCAS.2017.8050219Google Scholar
- C. Frenkel, M. Lefebvre, J.-D. Legat, and D. Bol. 2019. A 0.086-mm2 12.7-pJ/SOP 64k-synapse 256-neuron online-learning digital spiking neuromorphic processor in 28-nm CMOS. IEEE Trans. Biomedical Circuits Syst. 13, 1 (February 2019), 145–158. https://doi.org/10.1109/TBCAS.2018.2880425Google Scholar
- K Roy G Srinivasan, P Panda. 2018. STDP-based unsupervised feature learning using convolution-over-time in spiking neural networks for energy-efficient neuromorphic computing. ACM Journal on Emerging Technologies in Computing Systems 14, 4(2018), 44.Google Scholar
- L.R. Iyer, Y. Chua, and H. Li. 2018. Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain. arXiv:1807.01013 (2018).Google Scholar
- L. R. Iyer and A. Basu. 2017. Unsupervised learning of event-based image recordings using spike-timing-dependent plasticity. In Proc. of Intl. Joint Conf. on Neural Networks (IJCNN). Anchorage, AK, USA. https://doi.org/10.1109/IJCNN.2017.7966074Google Scholar
- S.R. Kherapidsheh, M. Ganjitabesh, S.J. Thorpe, and T. Masquelier. 2017. STDP-based spiking deep convolutional neural networks for object recognition. Neural Networks 99(2017), 56–67. https://doi.org/10.1016/j.neunet.2017.12.005Google ScholarDigital Library
- C. Lee, P. Panda, G. Srinivasan, and K. Roy. 2018. Training deep spiking convolutional neural networks with STDP-based unsupervised pre-training followed by supervised fine-tuning. Front. Neurosci. 12, 435 (2018). https://doi.org/10.3389/fnins.2018.00435Google Scholar
- S. Mitra, S. Fusi, and G. Indiveri. 2008. Real-time classification of complex patterns using spike-based learning in neuromorphic VLSI. IEEE Trans. Biomedical Circuits Syst. 1, 1 (February 2008), 32–42. https://doi.org/10.1109/TBCAS.2008.2005781Google Scholar
- M. Mozafari, M. Ganjitabesh, A. Nowzari-Dalini, S.J. Thorpe, and T. Masquelier. 2019. Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks. Pattern recognition 94(2019), 87–95. https://doi.org/10.1016/j.patcog.2019.05.015Google Scholar
- P. Panda and K. Roy. 2018. Unsupervised regenerative learning of hierarchical features in spiking deep networks for object recognition. In Intl Joint Conf. on Neural Networks.Google Scholar
- M. Pfeiffer and T. Pfeil. 2018. Deep learning with spiking neurons: opportunities and challenges. Front. Neurosci. 12, 774 (2018). https://doi.org/10.3389/fnins.2018.00774Google Scholar
- Spurious learning in networks with Spike Driven Synaptic Plasticity
Recommendations
Ryanodine-receptor-driven intracellular calcium dynamics underlying spatial association of synaptic plasticity
Synaptic modifications induced at one synapse are accompanied by hetero-synaptic changes at neighboring sites. In addition, it is suggested that the mechanism of spatial association of synaptic plasticity is based on intracellular calcium signaling that ...
Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity
The persistent modification of synaptic efficacy as a function of the relative timing of pre- and postsynaptic spikes is a phenomenon known as spike-timing-dependent plasticity (STDP). Here we show that the modulation of STDP by a global reward signal ...
Spike-Driven Synaptic Plasticity: Theory, Simulation, VLSI Implementation
We present a model for spike-driven dynamics of a plastic synapse, suited for aVLSI implementation. The synaptic device behaves as a capacitor on short timescales and preserves the memory of two stable states (efficacies) on long timescales. The ...
Comments