We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research. Our systems have a xed structure, invariant in time...
Shrinking transistor sizes and a trend toward low-power processors have caused increased leakage, high per-device variation and a larger number of hard and soft errors. Maintainin...
- The model of a simple perceptron using phase-encoded inputs and complex-valued weights is presented. Multilayer two-input and three-input complex-valued neurons (CVNs) are implem...
Howard E. Michel, David Rancour, Sushanth Iringent...
Selectiveattentionis a mechanismsused to sequentiallyselectthe spatiallocationsof salientregionsin the sensor’sfieldof view. This mechanism overcomesthe problem of flooding limi...
We describe an analog-VLSI neural network for face recognition based on subspace methods. The system uses a dimensionality-reduction network whose coefficients can be either progr...
Gonzalo Carvajal, Waldo Valenzuela, Miguel Figuero...