Title |
Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks
|
---|---|
Published in |
Frontiers in Neuroscience, December 2017
|
DOI | 10.3389/fnins.2017.00693 |
Pubmed ID | |
Authors |
Priyadarshini Panda, Kaushik Roy |
Abstract |
Synaptic Plasticity, the foundation for learning and memory formation in the human brain, manifests in various forms. Here, we combine the standard spike timing correlation based Hebbian plasticity with a non-Hebbian synaptic decay mechanism for training a recurrent spiking neural model to generate sequences. We show that inclusion of the adaptive decay of synaptic weights with standard STDP helps learn stable contextual dependencies between temporal sequences, while reducing the strong attractor states that emerge in recurrent models due to feedback loops. Furthermore, we show that the combined learning scheme suppresses the chaotic activity in the recurrent model substantially, thereby enhancing its' ability to generate sequences consistently even in the presence of perturbations. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 1 | 100% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 1 | 100% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 54 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 13 | 24% |
Student > Ph. D. Student | 10 | 19% |
Student > Doctoral Student | 7 | 13% |
Student > Master | 6 | 11% |
Student > Bachelor | 3 | 6% |
Other | 5 | 9% |
Unknown | 10 | 19% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 16 | 30% |
Computer Science | 10 | 19% |
Neuroscience | 4 | 7% |
Agricultural and Biological Sciences | 3 | 6% |
Physics and Astronomy | 3 | 6% |
Other | 7 | 13% |
Unknown | 11 | 20% |