Learning Only When Necessary: Better Memories of Correlated Patterns in Networks with Bounded Synapses
By Walter Senn, Stefano Fusi. 2005
49 citations recorded by the source corpus.
Subfields: Cellular and Molecular Neuroscience, Cognitive Neuroscience, Electrical and Electronic Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cellular and Molecular Neuroscience
- Fabio Stefanini
- Giacomo Indiveri
- Chiara Bartolozzi
- Walter Senn
- Ning Qiao
- Andrea Soltoggio
- Elisabetta Chicca
- Stefano Fusi
In Cognitive Neuroscience
- Giacomo Indiveri
- Fabio Stefanini
- Chiara Bartolozzi
- Stefano Fusi
- Andrea Soltoggio
- Ning Qiao
- Hesham Mostafa
- Walter Senn
In Electrical and Electronic Engineering
- Giacomo Indiveri
- Fabio Stefanini
- Chiara Bartolozzi
- Stefano Fusi
- Andrea Soltoggio
- Ning Qiao
- Hesham Mostafa
- Walter Senn
Citations in the corpus
- Short-term plasticity as cause–effect hypothesis testing in distal reward learning (2014, background): “In general, continuous learning, or synapses that are always plastic, pose a treat to previously acquired memory (Senn and Fusi, 2005; Fusi and Senn, 2006; Leibold and Kempter, 2008).”
- A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses (2015, background): “They have been shown to be effective in extending thememory lifetime of recurrent spiking neural networks, and in increasing their capacity (Senn and Fusi, 2005).”
- Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems (2014, methodology): “The conditions on VCa implement a ‘‘stop-learning’’ mechanism that greatly improves the generalization performance of the system by preventing overfitting when the input pattern has already been learned [24], [25].”
- Moderate Levels of Activation Lead to Forgetting In the Think/No-Think Paradigm (2013, unknown): “Newman et al., 2006; Norman et al., 2007), several other neural network models have been developed that instantiate some form of nonmonotonic plasticity (Bienenstock, Cooper, & Munro, 1982; Diederich & Opper, 1987; Gardner, 1988; Senn & Fusi, 2005; Vico & Jerez, 2003).”
- Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic Dynamics (2007, background): “When a single output neuron is considered, arbitrary linearly separable patterns can be learned without errors (Senn and Fusi, 2005b; Senn and Fusi, 2005a), as in the case of the simple perceptron.”