• Corpus ID: 245144547

Learning to track environment state via predictive autoencoding

  title={Learning to track environment state via predictive autoencoding},
  author={Marian Andrecki and Nicholas Kenelm Taylor},
This work introduces a neural architecture for learning forward models of stochastic environments. The task is achieved solely through learning from temporal unstructured observations in the form of images. Once trained, the model allows for tracking of the environment state in the presence of noise or with new percepts arriving intermittently. Additionally, the state estimate can be propagated in observation-blind mode, thus allowing for long-term predictions. The network can output both… 

Figures and Tables from this paper



Unsupervised Learning of Visual Structure using Predictive Generative Networks

It is argued that prediction can serve as a powerful unsupervised loss for learning rich internal representations of high-level object features in deep neural networks trained using a CNN-LSTM-deCNN framework.

Prediction Under Uncertainty with Error-Encoding Networks

In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling com- ponents of the future state which are

Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning

The results suggest that prediction represents a powerful framework for unsupervised learning, allowing for implicit learning of object and scene structure.

Asynchronous Methods for Deep Reinforcement Learning

A conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers and shows that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.

Deep multi-scale video prediction beyond mean square error

This work trains a convolutional network to generate future frames given an input sequence and proposes three different and complementary feature learning strategies: a multi-scale architecture, an adversarial training method, and an image gradient difference loss function.

An Introduction to Sequential Monte Carlo Methods

Many real-world data analysis tasks involve estimating unknown quantities from some given observations, and all inference on the unknown quantities is based on the posterior distribution obtained from Bayes’ theorem.

Action-Conditional Video Prediction using Deep Networks in Atari Games

This paper is the first to make and evaluate long-term predictions on high-dimensional video conditioned by control inputs and proposes and evaluates two deep neural network architectures that consist of encoding, action-conditional transformation, and decoding layers based on convolutional neural networks and recurrent neural networks.

Human-level control through deep reinforcement learning

This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

Unsupervised Learning of Video Representations using LSTMs

This work uses Long Short Term Memory networks to learn representations of video sequences and evaluates the representations by finetuning them for a supervised learning problem - human action recognition on the UCF-101 and HMDB-51 datasets.

Autoencoders, Unsupervised Learning, and Deep Architectures

  • P. Baldi
  • Computer Science
    ICML Unsupervised and Transfer Learning
  • 2012
The framework sheds light on the different kinds of autoencoders, their learning complexity, their horizontal and vertical composability in deep architectures, their critical points, and their fundamental connections to clustering, Hebbian learning, and information theory.