Architecture
Today I’d like to share a system architecture for autonomous intelligence proposed by Yann LeCun.
The architecture consists of the following modules.
- Perception
Perceive the world through multiple sensors and predict the current state - Actor
Predicts a sequence of possible actions based on the information from the Perception module - World Model
Predict plausible future states given the sequence of possible actions proposed by the Actor module while estimating missing information that didn’t make it to the Perception module. - Cost
Computes a “scalar” that measures the level of discomfort(If the state is painful, this value will be high. Conversely, if the state is comfortable, this value will be low) to have the Configurator module understand which actions/states to avoid. - Short-term Memory
Keep track of current and future states and the corresponding cost - Configurator
Takes input from all other elements and configures them to perform the task at hand.
