Title:
スパイキングニューラルネットワーク装置およびその学習方法
Document Type and Number:
Japanese Patent JP7118930
Kind Code:
B2
Abstract:
A spiking neural network device according to an embodiment includes a synaptic element, a neuron circuit, a synaptic potentiator, and a synaptic depressor. The synaptic element has a variable weight. The neuron circuit inputs a spike voltage having a magnitude adjusted in accordance with the weight of the synaptic element via the synaptic element, and fires when a predetermined condition is satisfied. The synaptic potentiator performs a potentiating operation for potentiating the weight of the synaptic element depending on input timing of the spike voltage and firing timing of the neuron circuit. The synaptic depressor performs a depression operation for depressing the weight of the synaptic element in accordance with a schedule independent from the input timing of the spike voltage and the firing timing of the neuron circuit.
More Like This:
Inventors:
Yoshifumi Nishi
Kumiko Nomura
Verdun Radu
Takao Marugame
Kumiko Nomura
Verdun Radu
Takao Marugame
Application Number:
JP2019149790A
Publication Date:
August 16, 2022
Filing Date:
August 19, 2019
Export Citation:
Assignee:
Toshiba Corporation
International Classes:
G06N3/04; G06N3/063
Domestic Patent References:
| JP2013534018A | ||||
| JP2014535118A | ||||
| JP2016530630A | ||||
| JP2019502970A | ||||
| JP2017526224A |
Foreign References:
| US20180357529 | ||||
| US20190122105 | ||||
| US20190138900 | ||||
| US20190213472 |
Other References:
PANDA, P. et al,Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks,Frontier in Neuroscience [online],2017年12月12日,Vol. 11,[retrieved on 2022-03-02], Retrieved from the Internet: ,
THOMAS, P., et al.,Is a 4-Bit Synaptic Weight Resolution Enough? - Constraints on Enabling Spike-Timing Dependent Plasticity in Neuromorphic Hardware,Frontiers in Neuroscience [online],2012年07月17日,Vol. 6,[retrieved on 2022-03-02], Retrieved from the Internet:,
STEPP, N., et al.,A Dynamical Systems Approach to Neuromorphic Computation of Conditional Probabilities,Proceedings of the International Conference on Neuromorphic Systems (ICONS '18) [online],2018年07月23日,pp. 1-4,[retrieved on 2022-03-02], Retrieved from the Internet:,
THOMAS, P., et al.,Is a 4-Bit Synaptic Weight Resolution Enough? - Constraints on Enabling Spike-Timing Dependent Plasticity in Neuromorphic Hardware,Frontiers in Neuroscience [online],2012年07月17日,Vol. 6,[retrieved on 2022-03-02], Retrieved from the Internet:
STEPP, N., et al.,A Dynamical Systems Approach to Neuromorphic Computation of Conditional Probabilities,Proceedings of the International Conference on Neuromorphic Systems (ICONS '18) [online],2018年07月23日,pp. 1-4,[retrieved on 2022-03-02], Retrieved from the Internet:
Attorney, Agent or Firm:
Sakai International Patent Office
Previous Patent: Apparatus for pressing and sticking pavement material and method for pressing and sticking
Next Patent: 直流サーボモータ
Next Patent: 直流サーボモータ