Brain Corporation

Olivier Coenen

Oleg Sinyavskiy

Eugene Izhikevich

Jean-Baptiste Passot

Vadim Polonichko

Filip Ponulak

Adaptive controller apparatus of a plant may be implemented. The controller may comprise an encoder block and a control block. The encoder may utilize basis function kernel expansion technique to encode an arbitrary combination of inputs into spike output. The controller may comprise spiking neuron network operable according to reinforcement learning process. The network may receive the encoder output via a plurality of plastic connections. The process may be configured to adaptively modify connection weights in order to maximize process performance, associated with a target outcome. The relevant features of the input may be identified and used for enabling the controlled plant to achieve the target outcome.

Spiking neuron network adaptive control apparatus and methods

Adaptive controller apparatus of a plant may be implemented. The controller may comprise an encoder block and a control block. The encoder may utilize basis function kernel expansion technique to encode an arbitrary combination of inputs into spike output. The controller may comprise spiking neuron network operable according to reinforcement learning process. The network may receive the encoder output via a plurality of plastic connections. The process may be configured to adaptively modify connection weights in order to maximize process performance, associated with a target outcome. The relevant features of the input may be identified and used for enabling the controlled plant to achieve the target outcome. The stochasticity of the learning process may be modulated. Stochasticity may be increased during initial stage of learning in order to encourage exploration. During subsequent controller operation, stochasticity may be reduced to reduce energy use by the controller.

Modulated stochasticity spiking neuron network controller apparatus and methods

Generalized learning rules may be implemented. A framework may be used to enable adaptive spiking neuron signal processing system to flexibly combine different learning rules (supervised, unsupervised, reinforcement learning) with different methods (online or batch learning). The generalized learning framework may employ time-averaged performance function as the learning measure thereby enabling modular architecture where learning tasks are separated from control tasks, so that changes in one of the modules do not necessitate changes within the other. Separation of learning tasks from the control tasks implementations may allow dynamic reconfiguration of the learning block in response to a task change or learning method change in real time. The generalized spiking neuron learning apparatus may be capable of implementing several learning rules concurrently based on the desired control application and without requiring users to explicitly identify the required learning rule composition for that task.

Systems and apparatus for implementing task-specific learning using spiking neurons

Adaptive proportional-integral-derivative controller apparatus of a plant may be implemented. The controller may comprise an encoder block utilizing basis function kernel expansion technique to encode an arbitrary combination of inputs into spike output. The basis function kernel may comprise one or more operators configured to manipulate basis components. The controller may comprise spiking neuron network operable according to reinforcement learning process. The network may receive the encoder output via a plurality of plastic connections. The process may be configured to adaptively modify connection weights in order to maximize process performance, associated with a target outcome. Features of the input may be identified and used for enabling the controlled plant to achieve the target outcome.

Proportional-integral-derivative controller effecting expansion kernels comprising a plurality of spiking neurons associated with a plurality of receptive fields

Framework may be implemented for transferring knowledge from an external agent to a robotic controller. In an obstacle avoidance/target approach application, the controller may be configured to determine a teaching signal based on a sensory input, the teaching signal conveying information associated with target action consistent with the sensory input, the sensory input being indicative of the target/obstacle. The controller may be configured to determine a control signal based on the sensory input, the control signal conveying information associated with target approach/avoidance action. The controller may determine a predicted control signal based on the sensory input and the teaching signal, the predicted control conveying information associated with the target action. The control signal may be combined with the predicted control in order to cause the robotic apparatus to execute the target action.

Apparatus and methods for reinforcement-guided supervised learning

Adaptive controller apparatus of a robot may be implemented. The controller may be operated in accordance with a reinforcement learning process. A trainer may observe movements of the robot and provide reinforcement signals to the controller via a remote clicker. The reinforcement may comprise one or more degrees of positive and/or negative reinforcement. Based on the reinforcement signal, the controller may adjust instantaneous cost and to modify controller implementation accordingly. Training via reinforcement combined with particular cost evaluations may enable the robot to move more like an animal.

Growing community of inventors

San Diego, CA, United States of America

Olivier Coenen