Sony France S.a.

Sony France

Frederic Kaplan

Pierre-Yves Oudeyer

Multiple parallel signal streams are produced by the sensors () associated with a device (). Events corresponding to real-world activities, contexts, environments, internal-states, uses, interactions and the like involving the device () can be detected in the multi-channel sensor-signal stream by evaluating how the pattern of coordination between the different sensors varies over time. The pattern of coordination between the sensors can be evaluated for a particular time period by computing an information distance matrix (IDM) for the sensor-signals generated during that time period. The IDM summarizes the normalized information distance between each possible pairing of the sensors.

Event-detection in multi-channel sensor-signal streams

In order to promote efficient learning of relationships inherent in a system or setup S described by system-state and context parameters, the next action to take, affecting the setup, is determined based on the knowledge gain expected to result from this action. Knowledge-gain is assessed 'locally' by comparing the value of a knowledge-indicator parameter after the action with the value of this indicator on one or more previous occasions when the system-state/context parameter(s) and action variable(s) had similar values to the current ones. Preferably the 'level of knowledge' is assessed based on the accuracy of predictions made by a prediction module. This technique can be applied to train a prediction machine by causing it to participate in the selection of a sequence of actions. This technique can also be applied for managing development of a self-developing device or system, the self-developing device or system performing a sequence of actions selected according to the action-selection technique.

Automated action-selection system and method, and application thereof to training prediction machines and driving the development of self-developing devices

A self-developing device () capable of open-ended development makes use of a special motivational system for selecting which action should be taken on the environment by an associated sensory-motor apparatus (). For a given candidate action, a motivational module () calculates a reward associated with the corresponding values that would be taken by one or more motivational variables that are independent of the nature of the associated sensory-motor apparatus. Preferred motivational variables are dependent on the developmental history of the device (), and include variables quantifying the predictability, familiarity and stability of sensory-motor variables serving as the inputs to the device (). The sensory-motor variables represent the status of the external environment and/or the internal resources () of the sensory-motor apparatus () whose behavior is controlled by the self-developing device (). Open-ended development is enabled by attributing a reward which is proportional to the rate of change of the history-dependent motivational variables.

Growing community of inventors

Paris, France

Frederic Kaplan