2014 · 44 citations · 7 references
Life SciencesComputer ScienceComputational NeuroscienceMachine LearningNeural EngineeringDendritic ComputationDendritic StructureLearning SystemsNeural NetworksPattern RecognitionSpiking Neural NetworksDendritic ArchitectureMulticlass ClassificationNeuromorphic DevicesNeuromorphic HardwareSparse ConnectivitySpiking Network ArchitecturesSpiking Neural Network ModelsSpiking Neuron Models
We present an architecture of a spike based multiclass classifier using neurons with non-linear dendrites and sparse synaptic connectivity where each synapse takes a binary value. The learning in this model happens not through weight updates but through structural changes, i.e. a change of connectivity between inputs and dendrites. Hence, it is well suited for implementation in neuromorphic systems using address event representation (AER). We present a new learning rule that allows better generalization of the system to noisy testing data making it feasible to transfer learnt weights in software to a hardware device interfacing with noisy spiking sensors. The new rule improves testing accuracy by 7 - 10% compared to earlier versions. We also present preliminary results for multi-class classification on handwritten digits from the MNIST database and show that our system can attain comparable performance (≈ 3% more error) with other reported spike based classifiers while using at least 50% less synaptic resources.
7
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Neural networks — A comprehensive foundation
Tadeusz Wilusz · Neurocomputing · 1995 · 2.9K citations
Real-time classification and sensor fusion with a spiking deep belief network
Peter O’Connor, Daniel Neil, Shih‐Chii Liu et al. · Frontiers in Neuroscience · 2013 · 411 citations · Full text