time constant
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.95)
Training biologically plausible recurrent neural networks on cognitive tasks with long-term dependencies Supplementary material A Demand for biological RNNs with long time-scale dependencies
Emergence of grid-like representations by training recurrent neural networks to perform spatial localization.
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
Country:
- North America > United States > New York (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology:
Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics
Niru Maheswaranathan, Alex Williams, Matthew Golub, Surya Ganguli, David Sussillo
Neural Information Processing Systems http://nips.cc/
Country:
- North America > United States > California > Santa Clara County > Stanford (0.05)
- North America > United States > California > Santa Clara County > Palo Alto (0.05)
- North America > United States > California > Santa Clara County > Mountain View (0.04)
- (2 more...)
Technology:
Country:
- Europe > Germany > Hamburg (0.04)
- Africa > Comoros > Grande Comore > Moroni (0.04)
- North America > United States > District of Columbia > Washington (0.04)
- (2 more...)
Technology:
A Appendix A.1 Linear Gaussian Model
We only expend a small amount of simulation budget to do this.
Latent Equilibrium
Paul Haider, Benjamin Ellenberger, Laura Kriener, Jakob Jordan, Walter Senn & Mihai A. Petrovici
A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons
Country:
- North America > United States (0.14)
- Asia > Middle East > Jordan (0.04)
Industry:
- Health & Medicine > Therapeutic Area > Neurology (0.94)
- Education (0.68)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
Unconditional stability of a recurrent neural circuit implementing divisive normalization
Further, for a generic recurrent weight matrix, we prove the stability of the 2D model and demonstrate empirically that stability holds in higher dimensions.
Country:
- North America > United States (0.14)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology: