18489327. SOLVING OPTIMIZATION PROBLEMS USING SPIKING NEUROMORPHIC NETWORK simplified abstract (Intel Corporation)
Contents
SOLVING OPTIMIZATION PROBLEMS USING SPIKING NEUROMORPHIC NETWORK
Organization Name
Inventor(s)
Narayan Srinivasa of San Jose CA (US)
SOLVING OPTIMIZATION PROBLEMS USING SPIKING NEUROMORPHIC NETWORK - A simplified explanation of the abstract
This abstract first appeared for US patent application 18489327 titled 'SOLVING OPTIMIZATION PROBLEMS USING SPIKING NEUROMORPHIC NETWORK
Simplified Explanation
- A spiking neuromorphic network is used to solve an optimization problem. - The network consists of primary neurons that represent variables of the optimization problem. - Primary neurons update their states and change variable values. - The network includes a cost neuron that computes costs based on variable values sent as spikes from primary neurons. - A minima neuron determines the lowest cost, while an integrator neuron tracks computational steps. - The minima or integrator neuron checks for convergence and instructs primary neurons to stop computing when achieved.
- Potential Applications:**
- Optimization problems in various fields such as engineering, finance, and logistics. - Machine learning tasks that require optimization of parameters.
- Problems Solved:**
- Efficiently solving complex optimization problems using a neuromorphic network. - Convergence monitoring and stopping computation when optimal solution is reached.
- Benefits:**
- Faster optimization process compared to traditional methods. - Adaptability to different types of optimization problems. - Potential for energy-efficient computing.
Original Abstract Submitted
A spiking neuromorphic network may be used to solve an optimization problem. The network may include primary neurons. The state of a primary neuron may be a value of a corresponding variable of the optimization problem. The primary neurons may update their states and change values of the variables. The network may also include a cost neuron that can compute, using a cost function, costs based on values of the variables sent to the cost neuron in the form of spikes from the primary neurons. The network may also include a minima neuron for determining the lowest cost and an integrator neuron for tracking how many computational steps the primary neurons have performed. The minima neuron or integrator neuron may determine whether convergence is achieved. After the convergence is achieved, the minima neuron or integrator neuron may instruct the primary neurons to stop computing new values of the variables.
