Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture

09/19/2018
by   Martin V. Butz, et al.
2

We introduce a dynamic artificial neural network-based (ANN) adaptive inference process, which learns temporal predictive models of dynamical systems. We term the process REPRISE, a REtrospective and PRospective Inference SchEme. REPRISE infers the unobservable contextual state that best explains its recently encountered sensorimotor experiences as well as accompanying, context-dependent temporal predictive models retrospectively. Meanwhile, it executes prospective inference, optimizing upcoming motor activities in a goal-directed manner. In a first implementation, a recurrent neural network (RNN) is trained to learn a temporal forward model, which predicts the sensorimotor contingencies of different simulated dynamic vehicles. The RNN is augmented with contextual neurons, which enable the compact encoding of distinct, but related sensorimotor dynamics. We show that REPRISE is able to concurrently learn to separate and approximate the encountered sensorimotor dynamics. Moreover, we show that REPRISE can exploit the learned model to induce goal-directed, model-predictive control, that is, approximate active inference: Given a goal state, the system imagines a motor command sequence optimizing it with the prospective objective to minimize the distance to a given goal. Meanwhile, the system evaluates the encountered sensorimotor contingencies retrospectively, adapting its neural hidden states for maintaining model coherence. The RNN activities thus continuously imagine the upcoming future and reflect on the recent past, optimizing both, hidden state and motor activities. In conclusion, the combination of temporal predictive structures with modulatory, generative encodings offers a way to develop compact event codes, which selectively activate particular types of sensorimotor event-specific dynamics.

READ FULL TEXT

page 4

page 9

page 12

research
02/23/2022

Inference of Affordances and Active Motor Control in Simulated Agents

Flexible, goal-directed behavior is a fundamental aspect of human life. ...
research
04/17/2018

Encoding Longer-term Contextual Multi-modal Information in a Predictive Coding Model

Studies suggest that within the hierarchical architecture, the topologic...
research
05/12/2021

Latent Event-Predictive Encodings through Counterfactual Regularization

A critical challenge for any intelligent system is to infer structure fr...
research
05/12/2020

Fostering Event Compression using Gated Surprise

Our brain receives a dynamically changing stream of sensorimotor data. Y...
research
06/04/2022

Developing hierarchical anticipations via neural network-based event segmentation

Humans can make predictions on various time scales and hierarchical leve...
research
02/26/2019

Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives

Voluntary behavior of humans appears to be composed of small, elementary...
research
05/27/2020

Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network

It is crucial to ask how agents can achieve goals by generating action p...

Please sign up or login with your details

Forgot password? Click here to reset